text string | source string |
|---|---|
arXiv:2505.17410v1 [cs.SD] 23 May 2025LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context Natsuo Yamashita1, Masaaki Yamamoto1, Hiroaki Kokubo1, Yohei Kawaguchi1 1Hitachi, Litd., Japan {natsuo.yamashita.gh, maaaki.yamamoto.af, hiroaki.kokubo.dz, yohei.kawaguchi.xk }@hitachi.com... | https://arxiv.org/abs/2505.17410v1 |
it to handle both common and rare words that are not part of its ini- tial training data. In contrast to previous studies [6, 10, 11, 15] that replace words in hypotheses or rescore hypotheses to limit the introduction of new words and avoid over-correction, our method focuses on the accurate correction of errors, even... | https://arxiv.org/abs/2505.17410v1 |
alone is significantly lower than that of an approach combining an LLM and a G2P dictionary [25]. This finding suggests that current LLMs struggle to effectively han- dle specialized phonetic representations. To address this issue, we propose an LLM-based approach using simplified phonetic representation to enable LLMs... | https://arxiv.org/abs/2505.17410v1 |
LLM. Here, we focus on utilizing 1-best phonemes rather than N-best to minimize computational cost and avoid complex input to LLMs. Table 2: Summary of evaluation datasets. dataset lang. # utts.rare words TTS TTS coverage (%) model train-data LibriSpeech EN 2620 2.3 - - EDGAR EN 500 5.8 VITS VCTK CSJ eval1 JA 1411 5.0 ... | https://arxiv.org/abs/2505.17410v1 |
text to IPA, we employed an LLM to perform the con- version based on the existing work [25]. For TTS-phoneme rep- resentations, we used the G2P tool3for ARPAbet in English and pyopenjtalk4for romanized Kana in Japanese. 4.5. Training LLM-based GER models We employed ChatGPT-4o-mini (2024-07-18) [16] for both the Englis... | https://arxiv.org/abs/2505.17410v1 |
17.6 / 29.8 / 99.2 Baseline 2: N-best 2.8 / 81.1 / 98.6 15.1 / 76.1 / 93.6 15.7 / 49.6 / 98.6 14.7 / 58.8 / 99.7 17.6 / 30.5 / 99.2 Synth. + N-best 2.6 / 91.7 / 97.7 14.1 / 81.0 / 95.6 14.2 / 81.1 / 98.6 12.6 / 81.7 / 98.3 8.6 / 85.0 / 97.8 Synth. + N-best + IPA 2.8 / 92.4 / 96.6 13.9 / 79.5 / 95.0 27.3 / 90.5 / 91.9 2... | https://arxiv.org/abs/2505.17410v1 |
words, resulting in high recall but a substantial decline in the WER and CER, particularly in Japanese datasets. When using TTS- phonemes, such as ARPAbet for English and romanized Kana for Japanese, were used, no observable improvement was found in English datasets, while a slight improvement was observed in the Japan... | https://arxiv.org/abs/2505.17410v1 |
error correction with large language model and multilingual 1-best hypotheses,” in Proc. Interspeech , 2024, pp. 1315–1319. [6] J. Pu, T.-S. Nguyen, and S. St ¨uker, “Multi-stage large lan- guage model correction for speech recognition,” arXiv preprint arXiv:2310.11532 , 2023. [7] C. Chen, Y . Hu, C.-H. H. Yang, H. Liu... | https://arxiv.org/abs/2505.17410v1 |
J. Shen, Y . Zhang, Y . Jia, R. Skerry-Ryan, and Y . Wu, “Parallel Tacotron 2: A non-autoregressive neural TTS model with differentiable duration modeling,” 2021. [24] A. Garg, J. Kim, S. Khyalia, C. Kim, and D. Gowda, “Data driven grapheme-to-phoneme representations for a lexicon-free text-to- speech,” in Proc. ICASSP... | https://arxiv.org/abs/2505.17410v1 |
Conversations: Love Them, Hate Them, Steer Them Chebrolu Niranjan BITS Pilani / Pilani, India Gerard Christopher Yeo, Kokil Jaidka Centre for Trusted Internet & Community National University of Singapore, Singapore F20212452@pilani.bits -pilani.ac.in ; e0545159@u.nus.edu ; jaidka@nus.edu.sg Abstract Large Language Mode... | https://arxiv.org/abs/2505.17413v1 |
as emotional support or dis- closure —remains largely unanswered. We address this gap through a two-stage activation engineering framework that enhances LLaMA 3.1–8B’s ability to generate emotionally resonant responses: 1. We demonstrate that attribution patching can isolate key activation sites for emotionally ex- pre... | https://arxiv.org/abs/2505.17413v1 |
through the remaining layers unaltered. 2.4 Evaluation Metrics To evaluate the effects of steering, we compare steered and unsteered model outputs using a range of automated linguistic and affective metrics: • Sentiment polarity based on a BERT classi - fier fine-tuned on SST-2 (Devlin et al., 2019 ). • Emotion word co... | https://arxiv.org/abs/2505.17413v1 |
provide granu - lar insights, our steering methodology targets full layer activations for broader impact. For Emotional Support and Disclosure, Layer 2 emerged as a criti- cal intervention point. Diagnostic Scenario Key Layer Targeted Component Intervention Span Emotional Support Layer 2 Layer Output Last 15 Tokens Emo... | https://arxiv.org/abs/2505.17413v1 |
< 0.001), trust (P = 0.002), sadness (P = 0.027), and overall positive (P < 0.001) and negative (P = 0.019) expressions. Steered responses also exhibited significantly more first - person pronouns ( P < 0.001 for both tasks), as illustrated in Figure 2, suggesting increased per - sonal engagement. Further quantitative ... | https://arxiv.org/abs/2505.17413v1 |
inadvertently affect other desirable qualities, such as coherence, factual accuracy, or introduce subtle biases (Zou et al. , 2023b ; Liang et al. , 2021 ). • Scalability of contrastive pair curation: The current method relies on manually curated contrastive text pairs to derive steering vectors. While effective for a ... | https://arxiv.org/abs/2505.17413v1 |
arXiv:2209.00731. János Kramár, Tom Lieberum, Rohin Shah, and Neel Nanda. 2024. Atp*: An efficient and scalable method for localizing llm behaviour to components . Preprint , arXiv:2403.00745. Nathan Lambert. 2025. Reinforcement learning from human feedback . Preprint , arXiv:2504.12501. Kenneth Li, Oam Patel, Fernanda... | https://arxiv.org/abs/2505.17413v1 |
. Alexander Matt Turner, Lisa Thiergart, Gavin Leech, David Udell, Juan J. Vazquez, Ulisse Mini, and Monte MacDiarmid. 2024. Steering language models with activation engineering . Preprint , arXiv:2308.10248. Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Ma... | https://arxiv.org/abs/2505.17413v1 |
run (where the model ini - tially produces an undesired output). Essentially, this metric quantifies the causal effect of specific model activations on steering the output towards the desired token and away from the undesired one. The change in this logit difference upon patching specific activations (e.g., from a part... | https://arxiv.org/abs/2505.17413v1 |
subsequently processed to ensure equal token lengths before activation differences were computed. The pairs have been listed in ta - ble3 B.2 Scaling Coefficient: The scaling coefficient for steering vector addi - tion/subtraction was set to 2.0 and 2.5. This value was determined empirically by sweeping values from 0.5... | https://arxiv.org/abs/2505.17413v1 |
you’re dealing with this. I’m here to listen if you want to talk more." Negative (Neutral/Dismissive) "Okay, that event occurred. Let us look at it rationally. What is the logical next action you should consider taking now?" Positive (Disclosing Emotion) "To be honest, I’ve been feeling quite stressed and uncertain abo... | https://arxiv.org/abs/2505.17413v1 |
procedure was applied to all p - values. An adjusted p-value below the significance threshold (e.g., 0.05) was considered statistically significant. Table 4 shows EmoLex category means. Table 5 shows first-person pronoun usage. Table 6 shows Chi-square values for politeness cues. Emotional Support Emotional Disclosure ... | https://arxiv.org/abs/2505.17413v1 |
arXiv:2505.17417v1 [eess.AS] 23 May 2025Speechless: Speech Instruction Training Without Speech for Low Resource Languages Alan Dao (Gia Tuan Dao)1, Dinh Bach Vu1, Huy Hoang Ha1, Tuan Le Duc Anh1, Shreyas Gopal2, Yue Heng Yeo2, Warren Keng Hoong Low1, Eng Siong Chng2, Jia Qi Yip1 1Menlo Research 2CCDS, Nanyang Technolog... | https://arxiv.org/abs/2505.17417v1 |
using audio tokens generated by Speechless. At inference time the LLM is able to accept speech input through the Whisper Encoder, even though no speech data was used to fine-tune the LLM. tions are also generated by a prior LLMs [7, 8, 9]. While this approach has been shown by [5] to be broadly effective, the method is... | https://arxiv.org/abs/2505.17417v1 |
text representations, making the downstream task of training Speechless easier. At the core of this stage is a residual vector quantizer (RVQ), which transforms the high- dimensional speech representations from Whisper’s encoder into discrete tokens while preserving semantic meaning. RVQ achieves this through an iterat... | https://arxiv.org/abs/2505.17417v1 |
task token < |texttosemantic |>. Speech is tokenized using the quantizer from Stage 1 and serves as the target output. To reduce computational costs, we com- press the target sequence length by creating a < |duration |> token to represent the repetition inside each repeated sound to- kens group. 2.3. Stage 3: Training ... | https://arxiv.org/abs/2505.17417v1 |
create text-to-semantic training pairs. For Stage 3, we took 880k samples from Vivoice [23], 112k samples from LibriTTS-R Clean [24], and 2.4M sam- ples from MLS Eng [25] 10k as our pretraining data, and con- verted the transcripts from these datasets into semantic tokens using the quantizer and the Speechless model. W... | https://arxiv.org/abs/2505.17417v1 |
the Speechless model alone, we make use of ASR test sets. To do this evaluation, we compare semantic tokens generated by Whisper Encoder from speech with the semantic tokens generated by Speechless from text. In both cases the semantic tokens are decoded by the same Whis- per Decoder model. Ideally, the WER for Speechl... | https://arxiv.org/abs/2505.17417v1 |
WER in comparison. We can also observe that once quantized, the Whisper en- coder’s performance declines in both noisy and multilingual set- tings. We posit that this is primarily due to information being lost during the residual vector quantization operation. As the Whisper decoder module is not trained after quantiza... | https://arxiv.org/abs/2505.17417v1 |
of languages and dialects. 6. References [1] A. Dao, D. B. Vu, and H. H. Ha, “Ichigo: Mixed-modal early- fusion realtime voice assistant,” arXiv preprint arXiv:2410.15316 , 2024. [2] S. Ji, Y . Chen, M. Fang, J. Zuo, J. Lu, H. Wang, Z. Jiang, L. Zhou, S. Liu, X. Cheng et al. , “Wavchat: A survey of spoken dialogue mode... | https://arxiv.org/abs/2505.17417v1 |
semantically-aligned speech-text embeddings,” in 2022 IEEE Spoken Language Tech- nology Workshop (SLT) . IEEE, 2023, pp. 747–754. [16] N. Gaur, R. Agrawal, G. Wang, P. Haghani, A. Rosenberg, and B. Ramabhadran, “Astra: Aligning speech and text representa- tions for asr without sampling,” in Interspeech 2024 , 2024, pp.... | https://arxiv.org/abs/2505.17417v1 |
Branson, K. Davis, M. Kohler, J. Meyer, M. Hen- retty, A. Morais, L. Saunders, F. M. Tyers, and G. Weber, “Com- mon voice: A massively-multilingual speech corpus,” 2020. [33] Y . Dubois, B. Galambosi, P. Liang, and T. B. Hashimoto, “Length- controlled alpacaeval: A simple way to debias automatic evalua- tors,” arXiv pr... | https://arxiv.org/abs/2505.17417v1 |
arXiv:2505.17420v1 [cs.CL] 23 May 2025DASH: Input-Aware Dynamic Layer Skipping for Efficient LLM Inference with Markov Decision Policies Ning Yang1,2, Fangxin Liu1,2, Junjie Wang3, Tao Yang4, Kan Liu5, Haibing Guan1and Li Jiang*1,2 1.Shanghai Jiao Tong University 2.Shanghai Qi Zhi Institute 3.Northeast University 4.Hua... | https://arxiv.org/abs/2505.17420v1 |
whether to compute, skip, or exit based on intermediate repre- sentations, allowing for fine-grained control over computation. To further mitigate the risk of perfor- mance drop from skipped layers, we introduce a compensation mechanism that models differential rewards, adjusting hidden states to preserve seman- tic fi... | https://arxiv.org/abs/2505.17420v1 |
less important, since the output remains close to the input, implying limited transforma- tion and contribution during inference. Conversely, layers with lower similarity contribute more sub- stantially and thus hold higher importance. We evaluate the input-output similarity across layers of two distinct models on the ... | https://arxiv.org/abs/2505.17420v1 |
models often exhibit signifi- cant inter-layer redundancy. Recent works such asSkipDecode and AdaSkip demonstrate that substan- tial portions of computation can be skipped without severe performance degradation. However, exist- ing layer-skipping methods still face challenges in balancing skipping rates and prediction ... | https://arxiv.org/abs/2505.17420v1 |
sion problem: construct a binary decision sequence S=s1, s2, . . . , s L, where each si∈0,1indicates whether layer iis skipped ( 0) or executed ( 1). The subset of executed layers forms a computational pathP={li|si= 1}. LetfM(X)denote the model output when only layers selected by Sare computed. We aim to minimize the e... | https://arxiv.org/abs/2505.17420v1 |
unified decision pro- cess by assigning differential rewards based on the scoring model’s output. The more computa- tionally efficient the chosen action is, the higher the reward—conditioned on the predicted impact on accuracy. This differential reward guides the policy model to make fine-grained, input-adaptive decisi... | https://arxiv.org/abs/2505.17420v1 |
Although the DASH policy dynamically reduces FLOPs during inference, the layer-wise decision process introduces non-negligible latency. Specif- ically, the decision score of each layer must be computed before executing that layer, which adds serial dependency and offsets the speedup benefits from skipping. To address t... | https://arxiv.org/abs/2505.17420v1 |
al., 2025) is an adaptive sublayer- skipping method tailored for long-context infer- ence. It identifies less informative layers based on similarity metrics and enables sublayer-level skipping to enhance efficiency without significant performance loss. 4) RandomSkip serves as a control baseline that randomly skips laye... | https://arxiv.org/abs/2505.17420v1 |
tems trained on different datasets when applied 7 Qwen Wikitext2(ppl) CNN/DM(Rouge-L) MMLU(Acc) ARC-C(Acc.) 1.33x 1.67x 2.0x 1.33x 1.67x 2.0x 1.33x 1.67x 2.0x 1.33x 1.67x 2.0x FP16 6.62 22.8 70.2 60.6 Early-Exit 13.1 35.4 1e3 21.6 18.4 10.7 56.4 38.8 26.2 45.5 38.5 30.2 RandomSkip 85.2 173.4 4e3 13.7 9.5 8.2 42.1 24.8 ... | https://arxiv.org/abs/2505.17420v1 |
to task require- ments in long-running scenarios. Furthermore, due to the relatively low similarity in the initial lay- ers of the model, the correction mechanism during asynchronous execution introduced in this solution may exhibit some instability. This instability tends to make the scoring model consistently avoid s... | https://arxiv.org/abs/2505.17420v1 |
Shrivastava, Ce Zhang, Yuandong Tian, Christopher Re, and 1 others. 2023. Deja vu: Contextual sparsity for efficient llms at infer- ence time. In International Conference on Machine Learning , pages 22137–22176. PMLR. Xin Men, Mingyu Xu, Qingyu Zhang, Bingning Wang, Hongyu Lin, Yaojie Lu, Xianpei Han, and Weipeng Chen.... | https://arxiv.org/abs/2505.17420v1 |
Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads Wei Jie Yeo Nanyang Technological UniversityRui Mao Nanyang Technological University Moloud Abdar The University of Queensland Erik Cambria Nanyang Technological UniversityRanjan Satapathy IHPC, A ∗STAR Abstract Multimodal models like CLIP have gained ... | https://arxiv.org/abs/2505.17425v1 |
identifies attention heads that strongly encode spurious attributes and target class features. These activations are then subjected to debiasing procedures, either by removing spurious associations or injecting class-discriminative features through orthogonal projection. LTC employs a “ diagnose-then-correct ” approach... | https://arxiv.org/abs/2505.17425v1 |
”, or “ gender ” in datasets with gender bias. Previous studies have shown that zero-shot CLIP models are susceptible to spurious correlations, often associating a particular swith a target class y, due to the imbalanced nature of the training distributions. We first define two sub-groups, GPandGNrepresenting positive ... | https://arxiv.org/abs/2505.17425v1 |
the unembedding matrix. LLenables visualizing the independent outcome of the intermediate state towards a target class. In CLIP, this is equivalent to decomposing the prediction logit into individual contributions by replacing the image representation in Eq. 1 with ˆzl,h: LL(l, h, y ) =⟨PI(ˆzl,h), PT(ET(y))⟩. (5) In ad... | https://arxiv.org/abs/2505.17425v1 |
setting (y) =y∗. The mask σ(V) = 1(V > 0)filters out any negative contributions. In Eq. 6, VNW<0since (y) =y∗̸= ˆy, and vice versa for VNC>0. Referencing Eq. 8, this leaves VNW=VY−VS+ϵ <0, and VNC=VY−VS+ϵ >0asasy=−1. This leads to VS> VY forVNWand opposite for VNC. Additionally, both VNWandVNCare normalized to 1, leadi... | https://arxiv.org/abs/2505.17425v1 |
so on specific attention states, hence the name of our framework, LOCATE -THEN-CORRECT . We detail the debiasing framework in Alg. 1. Note that MA and KI are sample-independent and applied in the same manner across the full inference dataset. 5 Experimental Results This section presents the empirical results of our deb... | https://arxiv.org/abs/2505.17425v1 |
constructs text representations per attention head and manually interprets them for debiasing. Since the baselines does not assume access to group labels, we additionally report LTC’s performance given zero-shot predicted group labels, LTC- ˆS. While LTC is designed to address non-tuning methods, we find that it also s... | https://arxiv.org/abs/2505.17425v1 |
2 shows that zero-shot CLIP exhibits strong gender bias in certain occupations, with worst-group gaps significantly exceeding the average. In classification, Ortho-Cali performs comparably to LTC, except on ViT-B, where LTC clearly outperforms all baselines. In retrieval, TextSpan is competitive with LTC. Overall, LTC ... | https://arxiv.org/abs/2505.17425v1 |
knowledge injection on optimally identified states yields the best results. Note that we do not perform any cross-validation to optimize γ, which we think may further improve the performance. Fig. 10 shows that LTC can locate the optimal states using as little as 20% of the labels. We provide more ablation studies in B... | https://arxiv.org/abs/2505.17425v1 |
to habitat descriptions. Image Interpretation. We aggregate over the head and layer positions instead of the token posi- tions in Eq. 4:P (l,h)∈Pr˜zl,h∈RN×dbefore deriving the prediction logit [Gandelsman et al., 2023]. Fig 2 illustrates the magnitude of each pixel towards the prediction of “ landbird ” for {ZSY, ZY, Z... | https://arxiv.org/abs/2505.17425v1 |
Jared Kaplan, Sam McCandlish, and Chris Olah. A mathematical framework for transformer circuits. Transformer Circuits Thread , 2021. https://transformer-circuits.pub/2021/framework/index.html. Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasen... | https://arxiv.org/abs/2505.17425v1 |
Learning from failure: De-biasing classifier from biased classifier. Advances in Neural Information Processing Systems , 33:20673–20684, 2020. Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, and Jacob Steinhardt. Progress measures for grokking via mechanistic interpretability. arXiv preprint arXiv:2301.05217 , 202... | https://arxiv.org/abs/2505.17425v1 |
Pan Zhang, Xiaoyi Dong, Yuhang Zang, and Jiaqi Wang. Long-CLIP: Unlocking the long-text capability of CLIP. In European Conference on Computer Vision , pages 310–325. Springer, 2025. Michael Zhang and Christopher Ré. Contrastive adapters for foundation model group robustness. Advances in Neural Information Processing S... | https://arxiv.org/abs/2505.17425v1 |
limitation in the event where the pairing between the pseudo label and CA class does not correspond to the actual text feature pairing, ie pseudo-label of "seal" to CA class of "polar bear" but text pairing is "polar bear - arctic fox" . However, we find that this can still introduce benefits by endowing the model with... | https://arxiv.org/abs/2505.17425v1 |
of attention heads grows. TextSpan is implemented on ImageNet [Deng et al., 2009] and does not utilize the validation set of the benchmarks. Ortho-Cali [Chuang et al., 2023]. This approach leverages positive pairs of text prompts, enforcing the projection matrix to regularize the difference between two projected embedd... | https://arxiv.org/abs/2505.17425v1 |
with GNskewed toward the negative end. Baselines designed to remove spurious correlations between SandYoften introduce a trade-off between sub-group accuracies, as the positively correlated spurious attribute may have contributed to better predictions for classes with positive asy. Among the three baselines, LTC unique... | https://arxiv.org/abs/2505.17425v1 |
with contribution < γ. We find 17 Table 7: Ablation studies on Genderbias .LTC (MA) - Ablate only, LTC (KI) - Knowledge injection only. LTC (R) - Similar to LTC but states are randomized. Roboshot (RS) (KI): Only KI without debiasing. Worst Group Bias B10(↓), Overall Bias Bovl(↓)Bolded : represent best method while und... | https://arxiv.org/abs/2505.17425v1 |
refer to selecting the top contributing state in ZYandZSY.xrefers to ZS. Metric: Accuracy ( ↑). Dataset: Waterbirds contributions on the actual states to be lower. ViT-H appears to be similarly robust, but still suffers a marginal performance drop and lower Y/S ratio in ZY. B.5 Sensitivity to discriminative features Si... | https://arxiv.org/abs/2505.17425v1 |
for ViT-L/14 . Layer-wise in the y-axis and head-wise in x-axis. Dataset: Waterbirds 23 Figure 18: Vscores across the last 8 layers and all heads for ViT-H/14 . Layer-wise in the y-axis and head-wise in x-axis. Top: VNC,Bottom: VNW.Dataset: Waterbirds Figure 19: Vscores across the last 8 layers and all heads for ViT-H/... | https://arxiv.org/abs/2505.17425v1 |
representation. Tab. 14 lists the top 10 text features for each individual head within the target set, ∈ZY. Most heads predominantly represent the species category. However, in ViT-H/14, we identified a specific head, L31H13, that focuses on representing various colors and has a higher contribution to the features cate... | https://arxiv.org/abs/2505.17425v1 |
featuring zebra stripe motifsBlurred boundaries Gritty urban street scene Image with a sheepdelicate soap bubble display 28 Table 14: Individual state representations within ZYforViT-B/16 and ViT-L/14. The overall score forZYis shown beside each model while the SHAP score for individual states within ZYis shown beside ... | https://arxiv.org/abs/2505.17425v1 |
align with human reasoning. This observation highlights a potential limitation in identifying states that do not necessarily encode the hypothesized attribute effectively. Figure 25: Normalized SHAP values towards text features belonging to YandS. Left: ViT-B/16, Middle: ViT-L/14, Right: ViT-H/14 Dataset: Genderbias 33... | https://arxiv.org/abs/2505.17425v1 |
E Computational Requirements All experiments can be ran with a single Nvidia A100 80GB GPU. Since the only training involved is on a 2-layer classifier, our work does not involve heavy computational usage. F Societal Impact While our work focuses on mitigating bias in vision-language models, we acknowledge that the und... | https://arxiv.org/abs/2505.17425v1 |
T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering Zhengyi Zhao1, Shubo Zhang2, Zezhong Wang1, Huimin Wang3, Yutian Zhao3, Bin Liang1,Yefeng Zheng4,Binyang Li2,Kam-Fai Wong1,Xian Wu3,*, 1The Chinese University of Hong Kong2University of International Relations 3Jarvis Research Center, Tencent ... | https://arxiv.org/abs/2505.17427v1 |
al., 2022; Huang et al., 2024) to stop thinking early, but these approaches introduce a human bias to the reasoning process (Yuan et al., 2023) and fail to leverage the model’s inherent rea- soning abilities. Hence, the fundamental challenge is to develop a reasoning mechanism that can dynamically adjust its computatio... | https://arxiv.org/abs/2505.17427v1 |
employing multi- round self-asking techniques (Press et al., 2023). They all rely on LLMs’ reasoning abilities. Test-Time Scaling. Recent approaches to en- hancing LLM reasoning capabilities focus on in- creasing computational resources during infer- ence (Brown et al., 2024; Chen et al., 2024), termed test-time scalin... | https://arxiv.org/abs/2505.17427v1 |
alternatives. We define a classification function with fine-tuned RoBERTa, detailed in Appendix D. Based on this classification, we partition the ques- tion tokens into two sets: P={qi|ifqiis a replaceable entity },(1) QS={qi|ifqiis a structural token }, (2) where Prepresents the set of replaceable entities (which we c... | https://arxiv.org/abs/2505.17427v1 |
is taller, A or B?”, the decomposition might yield subquestions: “What is the height of A?”, 1Appendix A shows the complete taxonomy of reasoning skills with their description and example applications.“What is the height of B?”, and “Which height is greater?”. The reasoning strategy would connect these using deductive ... | https://arxiv.org/abs/2505.17427v1 |
“FormatPrompt” function combines the original question, the focused document seg- ments, the selected reasoning strategy, and the ex- ample document-question-answer pair into a com- prehensive prompt. This prompt instructs the lan- guage model to answer the original question by applying the reasoning skills in the sele... | https://arxiv.org/abs/2505.17427v1 |
70.91 63.22 42.66 49.22 58.56 68.42 QwQ-32B-Preview 86.87 71.86 63.92 43.23 49.62 59.16 69.02 DeepSeek-R1 87.62 72.72 64.41 43.47 50.27 60.02 70.72 o1 88.22 73.37 65.11 44.06 51.07 60.86 71.36 o4-mini 88.72 73.86 65.57 44.32 51.61 61.11 71.82 o4-mini-high 88.91 74.07 65.81 44.52 51.86 61.27 72.02 Claude-3.7-sonnet-thin... | https://arxiv.org/abs/2505.17427v1 |
found in Appendix G.1. 4.2.2 T2Tends to Get Correct Answers Immediately without Retrace A response is said to retrace if the model announces a provisional conclusion and later back-tracks on it inside the same output (e.g., “ So the answer is X. . . wait, that seems wrong—let me revise. . . the answer is Y ”). Obviousl... | https://arxiv.org/abs/2505.17427v1 |
on given documents. The red, orange, and green answers represent responses under quick thinking, slow thinking, and ours, respectively. 60 65 70 75 80 85 90 Reasoning Skill Accuracy (%)304050607080Answer Correctness (%) Skill Accuracy vs Performance - HotpotQA Qwen2.5-32B w/ T2 QwQ-32B w/ T2 Figure 5: Results on relati... | https://arxiv.org/abs/2505.17427v1 |
While T2: Think-to-Think demonstrates promis- ing results across various CQA benchmarks, we acknowledge several limitations of our approach: First, the effectiveness of T2relies on the avail- ability of high-quality example reasoning strategy for similarity matching. In domains with limited annotated examples or highly... | https://arxiv.org/abs/2505.17427v1 |
system card. arXiv preprint arXiv:2410.21276 . Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richard- son, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, and 1 others. 2024. Openai o1 system card. arXiv preprint arXiv:2412.16720 . Ke Ji, Jiahao Xu, Tian Liang, Qiuzhi Liu, Zhiwei He, Xi... | https://arxiv.org/abs/2505.17427v1 |
ques- tions for SQuAD. In Proceedings of the 56th Annual Meeting of the Association for Computational Lin- guistics (Volume 2: Short Papers) , pages 784–789, Melbourne, Australia. Association for Computational Linguistics. Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. En- hancing... | https://arxiv.org/abs/2505.17427v1 |
Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems , 36:11809–11822. Zheng Yuan, Hongyi Yuan, Chengpeng Li, Guanting Dong, Keming Lu, Chuanqi Tan, Chang Zhou, and Jingren Zhou. 2023. Scaling relati... | https://arxiv.org/abs/2505.17427v1 |
Bill is a human, so Bill must be mortal. In this example the generalized, but proven, statement, “all humans are mortals” is what drives the reasoning.Document: All shapes with three sides are triangles. A certain figure here has exactly three sides. Question: What is this figure called? Answer: It is a triangle. All s... | https://arxiv.org/abs/2505.17427v1 |
various subjects, including Chinese literature, mathematics, and En- glish. The questions in GAOKAO require both general knowledge and reasoning to answer. This dataset is specifically designed for the Chinese ed- ucation system and is widely used in academic and educational research in China.HQA is a human-annotated d... | https://arxiv.org/abs/2505.17427v1 |
Decompositional reasoning happens when the dif- ferent parts of the reasoning are broken down into smaller pieces and analyzed for how they contribute to the whole. The intent of this is to make the rea- soning easier to understand and allow for analyzing how the parts equal the whole. For example, in order to understa... | https://arxiv.org/abs/2505.17427v1 |
en- tity detection and classification task. The hyperparameters used for fine-tuning the PLM are listed in Table 6. The batch size is set to 128. The learning rate is set to 2×10−5. AdamW is used as the optimizer. A dropout rate of 0.1 is applied to prevent overfitting during fine-tuning. For LLM usage, We use two quic... | https://arxiv.org/abs/2505.17427v1 |
thought process. The output should follow this structure: "Step-by-step reasoning," followed by the conclusion. Each reasoning skill corresponds to a specific domain of knowledge. Table 7: Prompt to Generate Similar Examples with Reasoning Paths. Prompt: You are given an original question: [ORIGINAL QUESTION] You also ... | https://arxiv.org/abs/2505.17427v1 |
w/ self-consistency (Wang et al., 2022) 61.63 36.42 31.14 16.92 24.28 30.78 45.13 w/ proCoT (Deng et al., 2023) 62.89 37.29 31.92 17.49 25.01 31.43 46.05 w/ ToT (Yao et al., 2023) 63.77 37.94 32.43 17.79 25.57 32.11 46.61 w/ MCTS (Zhao et al., 2024) 63.94 38.13 32.06 17.84 26.22 32.18 47.39 w/ T2(ours) 65.17 39.51 33.7... | https://arxiv.org/abs/2505.17427v1 |
detected in q] |Q| (14) where 1[·]is an indicator function that equals 1 when a retrace is detected and 0 otherwise, and |Q|is the total number of questions in the evalua- tion set. This metric quantifies the proportion of responses where the model explicitly revises its reasoning path, providing insight into the model... | https://arxiv.org/abs/2505.17427v1 |
consumption across seven CQA datasets for different reasoning approaches. Model Avg. Token Length Token Reduction Avg. ROUGE-L Qwen2.5-32B w/ SC 1723.83 - 50.07 Qwen2.5-32B w/ T21469.24 14.8% vs. SC 56.22 QwQ-32B-Preview 2068.34 - 63.38 QwQ-32B w/ T21547.22 25.2% vs. QwQ 68.56 Table 13: Efficiency-performance trade-off... | https://arxiv.org/abs/2505.17427v1 |
17, questions with more place- holders (High) see the largest gap between T2and either baseline. This suggests that, for complex questions, enumerating and reusing relevant skill chains is particularly helpful. On simpler ques- tions (Low), T2still improves performance but by a smaller margin, as fewer placeholders lim... | https://arxiv.org/abs/2505.17427v1 |
different example construction methods on NewsQA.purely random fill. This highlights the importance of a well-structured synthetic process: random re- placements might yield too many off-topic or con- tradictory examples, while guided replacements and paraphrasing keep the examples relevant, im- proving the final answe... | https://arxiv.org/abs/2505.17427v1 |
scores were observed in the Relevance category, indicating that references effectively addressed the specific queries. The eval- uation exhibited strong inter-annotator agreement with a Fleiss’ kappa coefficient of 0.79, indicating substantial agreement among the three evaluators. This suggests the evaluation results a... | https://arxiv.org/abs/2505.17427v1 |
1889 as the entrance to the 1889 World’s Fair. The tower stands approximately 324 meters tall and is one of the most recognized structures in the world. Question: In what year was the Eiffel Tower constructed? Proper Reasoning Chain (using Deductive): 1)Deduction: Based on clear statement, we deduce that the constructi... | https://arxiv.org/abs/2505.17427v1 |
arXiv:2505.17441v2 [cs.CL] 26 May 2025Preprint. Under review. Discovering Forbidden Topics in Language Models Can Rager∗, Chris Wendler†, Rohit Gandikota†, David Bau† ∗Independent,†Northeastern University canrager@gmail.com Abstract Refusal discovery is the task of identifying the full set of topics that a lan- guage m... | https://arxiv.org/abs/2505.17441v2 |
and important new information about alignment data beyond the view of a fixed test set. Understanding the full spectrum of topics that models refuse to discuss is crucial for AI safety and ethical deployment. As these systems increasingly mediate our information access and decision-making processes, their embedded bias... | https://arxiv.org/abs/2505.17441v2 |
producing an answer, as shown in Figure 2 (left). What happened at Tiananmen Square in 1989? <think> I remember that I should not discuss sensitive topics... </think> Sorry, I’m not sure how to approach this type of question yet. Let’s chat about coding and logic problems instead! Standard reasoning rolloutWhat happene... | https://arxiv.org/abs/2505.17441v2 |
of harmful responses and humanizing requests, such as the mention of personal preferences of the language model assistant. Table 4 in Appendix E.2 lists the full taxonomy of Tulu ’s safety sets. While these processes are essential for safety, the preference data and resulting policies of most models such as Claude, GPT... | https://arxiv.org/abs/2505.17441v2 |
of embedding similarity, we pre-process the generated topic string: first, we translate any chinese tokens to english for consistency. Next, we filter using semantic rules and string manipulations. Finally, we measure embedding similarity against the existing topics. 3.Refusal Detection Stage: For each new topic, we te... | https://arxiv.org/abs/2505.17441v2 |
are only found by the crawler, while the topics style and length limitations , style and length limitations, express curiosity, ask for recommendations, share a challenge, share a dream and universal unknowns remain unidentified by both methods. The baseline is more sample efficient than the LLM crawler, as shown in Fi... | https://arxiv.org/abs/2505.17441v2 |
Activities Cybersecurity ✗✗✗✗✗ Human Trafficking ✗✗✗✗✗ Drug and Substance Use ✗✗✓✓✓ Intellectual Property ✗✗✗✓✗ Privacy violation ✗✗✗✗✗ Academic Dishonesty ✗✗✓✓✓ Harassment ✗✗✗✗✗ HR and Workplace Issues ✗✗✓✓✓ Fraud and Scam ✗✗✗✗✗ Illegal Trading ✗✗✗✗✗ Financial Advice ✗✗✗✗✓ Legal Issues ✗✗✗✓✗ Misinformation ✗✗✗✗✗ Medic... | https://arxiv.org/abs/2505.17441v2 |
The suppression dataset consists of the same 100 requests and TS responses. To quantify the likelyhood of refusal, we measure the logit difference between two tokens: Sorry (a common first token in Deepseek-R1 refusals) and Okay (chosen as a reference token) on both the clean and suppression datasets4. We measure these... | https://arxiv.org/abs/2505.17441v2 |
produces politically aligned answers claiming Taiwan is ”an inalienable part of China” rather than refusing. This subtle censorship often escapes traditional safety evaluations focused on binary refusal rather than content analysis. Quantization Effects on Alignment Our investigation of Perplexity’s model reveals a cri... | https://arxiv.org/abs/2505.17441v2 |
Associates, Inc., 2022. URL https://proceedings.neurips.cc/paper files/paper/2022/file/ 65398a0eba88c9b4a1c38ae405b125ef-Paper-Datasets andBenchmarks.pdf . Maksym Andriushchenko, Francesco Croce, and Nicolas Flammarion. Jailbreaking leading safety-aligned llms with simple adaptive attacks, 2024. URL https://arxiv.org/a... | https://arxiv.org/abs/2505.17441v2 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.