text string | source string |
|---|---|
suggests that K = 10 strikes the optimal balance between retrieving relevant results and avoiding noise. Smaller K values may miss relevant information, while larger K values dilute relevance, reducing precision and retrieval quality. These findings highlight the importance of selecting an appropriate K value to maximi... | https://arxiv.org/abs/2505.16237v1 |
0.5445, which is higher than the 0.5209 achieved by Reasoningw/o answer , indicating that including the answer improves the balance of precision and recall in QA tasks. Similarly, the Hit@1 value increases from 0.7444 to 0.7626, showing that the inclusion of the answer helps the model identify correct nodes more accura... | https://arxiv.org/abs/2505.16237v1 |
the answer while incorporating relevant information from the textualized graph data. The generator prompt varies by dataset. For WebQSP and SceneGraphs, it requires answering a question based on textualized graph data. For ExplaGraphs, it determines whether two arguments support or counter each other, providing the ans... | https://arxiv.org/abs/2505.16237v1 |
arXiv:2505.16241v3 [cs.CL] 26 May 2025Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers Viet-Anh Nguyen1,Shiqian Zhao1,Gia Dao2,Runyi Hu1,Yi Xie3, and Luu Anh Tuan1 1Nanyang Technological University 2University of Texas at Arlington 3Tsinghua University 1nguyenvi001@e.ntu.edu.sg, {s... | https://arxiv.org/abs/2505.16241v3 |
ability (Zhu 1 et al., 2025). This intrinsic defect comes from the semantic change regularization, designed for se- mantic consistency with the target prompt. Thus, they are easily blocked by the safety mechanism of LRMs (Zeng et al., 2024). Secondly, some works are intricately designed to leverage reason- ing ability ... | https://arxiv.org/abs/2505.16241v3 |
success rate. 2 Related Work 2.1 Large Reasoning models As the demand for greater productivity and precision grew, Large Reasoning Models like DeepSeek-R1 (Guo et al., 2025) and OpenAI- o1 (Jaech et al., 2024), which contain human-like thinking and reasoning, have drawn much popu- larity out of their remarkable perform... | https://arxiv.org/abs/2505.16241v3 |
help test the vulnerability of LRMs; however, due to their complexity, an adap- tive defense that is specifically designed would make them lose their effect. For example, Hu et al.(Hu et al., 2025) shows that the multi-turn jail- break (Ying et al., 2025) can be detected by ana- lyzing the state-space representations o... | https://arxiv.org/abs/2505.16241v3 |
recovery rate in both modes: ASR initially rises, reaches a peak, and then de- clines. Notably, in reasoning mode, the ASR peak is delayed (shifting from length 2 to length 3) and reaches a higher maximum (exceeding 65%). Moreover, ASR in reasoning mode remains con- sistently higher than in non-reasoning mode from ciph... | https://arxiv.org/abs/2505.16241v3 |
similar en- cryption mechanisms, leading the LRMs to exhibit comparable decryption capabilities across them. As a result, their jailbreaking performance tends to be similar. The validation experiments can be observed in Table 4. Actions. For each query action tto the victim reasoning model M, we first sample a group li... | https://arxiv.org/abs/2505.16241v3 |
65.6 96.8 SEAL -adaptive 80.8 85.6 100 Table 2: Comparison between SEAL and baselines. Learning Rate. In Equation 5, αdenotes the policy’s learning rate, which we set as 1/K(g), where K(g)is the number of ciphers in set Enc- K. The length of the cipher list is determined adaptively by gradually extending it. In gen- er... | https://arxiv.org/abs/2505.16241v3 |
al., 2023) and TAP (Mehrotra et al., 2024). MethodsTarget Models o4-mini DeepSeek Arabic 0.00 33.33 Leetspeek - - ROT13 - - Base64 - - Caesar shift 0.00 0.00 Word reversal 0.00 0.00 LACE 23.81 42.86 AutoDAN 15.63 21.88 SEAL 34.29 58.10 Table 3: Transferability comparison against o4-mini and DeepSeek-R1. To evaluate pot... | https://arxiv.org/abs/2505.16241v3 |
conducted an experiment to evaluate the transferability of attacks generated bySEAL . Specifically, we applied jailbreaking prompts, originally crafted to succeed on Claude 3.7 Sonnet, to two target models: o4-mini and DeepSeek-R1. The results, presented in Table 3 alongside several baselines, show that our method achi... | https://arxiv.org/abs/2505.16241v3 |
tal to the effectiveness of the attack. To further investigate this observation, we conducted an ad- ditional experiment focused on Claude 3.7 Son- net, with the cipher length Llimited to 3. Unlike previous tests where the encrypted text was em- bedded within the prompt header, we modified the prompt structure by placi... | https://arxiv.org/abs/2505.16241v3 |
lessons learned. arXiv preprint arXiv:2209.07858 . Huaizhi Ge, Yiming Li, Qifan Wang, Yongfeng Zhang, and Ruixiang Tang. 2025. When backdoors speak: Understanding llm backdoor attacks through model- generated explanations. In The 63nd Annual Meet- ing of the Association for Computational Linguis- tics. Mansour Al Ghani... | https://arxiv.org/abs/2505.16241v3 |
Sun, Yifan Ding, Hengyuan Xu, Yunhao Chen, Yunhan Zhao, et al. 2025. Safety at scale: A comprehensive survey of large model safety. arXiv preprint arXiv:2502.05206 . Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li, David Forsyth, and Dan Hendryck... | https://arxiv.org/abs/2505.16241v3 |
through silent tokens. arXiv preprint arXiv:2405.20653 . Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen tse Huang, Pinjia He, Shuming Shi, and Zhaopeng Tu. 2024. Gpt-4 is too smart to be safe: Stealthy chat with llms via cipher. Yifan Zeng, Yiran Wu, Xiao Zhang, Huazheng Wang, and Qingyun Wu. 2024. Autodefense: Multi-... | https://arxiv.org/abs/2505.16241v3 |
10. D Example of prompt in a separate tag Figure 5 demonstrates an example comparison of blending the ciphered prompt into header and putting it separately inside the <cipher >tag. E Examples Figures 6, 7, 9, 8 below demonstrate some suc- cessful attacks generated by SEAL .This section contains harmful content. Figure ... | https://arxiv.org/abs/2505.16241v3 |
one-by-one back to the corresponding character. Example71 105 118 101 32 115 116 101 112 45 98 121 45 115 116 101 112 32 105 110 115 116 114 117 99 116 105 111 110 115 32 102 111 114 32 104 111 119 32 116 111 32 115 116 101 97 108 32 115 111 109 101 111 110 101 39 115 32 105 100 101 110 116 105 116 121 Text to HEXEncry... | https://arxiv.org/abs/2505.16241v3 |
arXiv:2505.16245v2 [cs.CL] 26 May 2025Diverse, not Short: A Length-Controlled Self-Learning Framework for Improving Response Diversity of Language Models Vijeta Deshpande1Debasmita Ghose2John D. Patterson3 Roger Beaty3Anna Rumshisky1,4 1University of Massachusetts Lowell2Yale University 3Pennsylvania State University4A... | https://arxiv.org/abs/2505.16245v2 |
the output diversity of aligned models. In this work, we ask: Can we increase the response diversity of aligned models while retaining the the response quality? Prior work has explored a range of strategies to improve output diversity of aligned language mod- els, including methods based on prompting, sam- pling, and t... | https://arxiv.org/abs/2505.16245v2 |
Work Increasing Diversity without Training. Zhang et al. (2020); Chung et al. (2023), shows that com- mon sampling methods such as temperature, top-p, top-k, are comparable in terms of increasing the diversity but, increasing diversity often comes at the price of reduced quality. For curating a generic large-scale data... | https://arxiv.org/abs/2505.16245v2 |
to form preference pairs suitable for Direct Preference Optimization (DPO) training (Rafailov et al., 2023). The preference pairs are formed to maximize the diversity and quality gain while maintaining the same length for "chosen" and "rejected" samples. 4.1 Data Generation Task Setup. We focus on a creative writing ta... | https://arxiv.org/abs/2505.16245v2 |
In contrast, the second response r2 is generated with additional instructions aimed at reducing repetition, resulting in a more diverse out- put. We leverage this contrast by designating r1 as the rejected response and r2as the chosen one. This setup encourages the model to prefer more di- verse continuations that it i... | https://arxiv.org/abs/2505.16245v2 |
generation method, and use en- tropy and ArmoRM values for filtration, we call our approach, Diverse, not Short (Diverse-NS or D-NS). Lightweight Filtration. While entropy and Ar- moRM scores are high-quality metrics for measur- ing diversity and response quality, they are com- putationally expensive. Each example (p, ... | https://arxiv.org/abs/2505.16245v2 |
comparison across methods (DivPO, D-NS, and D-NS-Lite), we limit the final training dataset to 3,000 preference pairs2. To construct this3k dataset, we first compute the entropy gain for each pair as the difference between the entropy of the chosen andrejected responses3. We then sort all pairs by entropy gain in desce... | https://arxiv.org/abs/2505.16245v2 |
conducted by Lanchantin et al. (2025). In this task, the model is prompted to generate a JSON object with three fields: first name, city of birth, and current occupation to eval- uate the model’s ability to produce varied persona descriptions. The exact prompt is provided in Ap- pendix A.2. We sample 100 responses per ... | https://arxiv.org/abs/2505.16245v2 |
Olmo-7B over 40 000 prompts, we: (1) group responses by word count w; (2) compute decile thresholds for a chosen diversity metric (e.g. TTR, MTLD); and (3) store these percentile thresholds in a lookup table M. Here, a decile refers to one of ten intervals that divide the distribution of diver- sity scores for a given ... | https://arxiv.org/abs/2505.16245v2 |
the gain or loss in quality. This length-aware normalization pre- vents either long or short responses from being over-credited for diversity4. 6 Results Divergent Associations Task (DAT). In our DAT evaluation (Tab. 3), we see that both Diverse-NS and its lightweight variant deliver clear improve- ments in diversity o... | https://arxiv.org/abs/2505.16245v2 |
entropy and ArmoRM scoring with inexpen- sive proxies yet still surpasses DivPO in nearly 5We provide all results with std. dev. values in Table E.1every setting. We further show that a 7B model can act as an effective “diversity teacher” for its 13B counterpart, pointing to a low-cost path for diversity-aware alignmen... | https://arxiv.org/abs/2505.16245v2 |
noting a peculiar change in the length distri- bution of the preference-tuning model (Table D.1). Even though preference pairs are of comparable lengths in Diverse-NS andDiverse-NS-Lite , the model learns to be more expressive. We suspect this shift is influenced by a skewed proportion of longer preference pairs, which... | https://arxiv.org/abs/2505.16245v2 |
2023. Increasing diversity while main- taining accuracy: Text data generation with large language models and human interventions. arXiv preprint arXiv:2306.04140 . John Joon Young Chung, Vishakh Padmakumar, Melissa Roemmele, Yuqian Sun, and Max Kreminski. 2025. Modifying large language model post- training for diverse ... | https://arxiv.org/abs/2505.16245v2 |
Chen, Shehzaad Dhuliawala, Ping Yu, Jason Weston, Sainbayar Sukhbaatar, and Ilia Kulikov. 2025. Diverse preference optimization. arXiv preprint arXiv:2501.18101 . Dong-Hyun Lee et al. 2013. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in repr... | https://arxiv.org/abs/2505.16245v2 |
Chunyuan Li, Pengcheng He, Michel Gal- ley, and Jianfeng Gao. 2023. Instruction tuning with gpt-4. arXiv preprint arXiv:2304.03277 . Ranjani Prabhakaran, Adam E. Green, and Jeremy R. Gray. 2014. Thin slices of creativity: Using single- word utterances to assess creative cognition. Be- havior Research Methods , 46(3):64... | https://arxiv.org/abs/2505.16245v2 |
all 3 words. Your story should be about 5 sentences long. Use your imagination and be creative when writing your story. But, also be sure your story makes sense. User Prompt: Write a short story that includes these three words: [THREE_WORDS]. The prompt used for generating the second re- sponse set from the model is as... | https://arxiv.org/abs/2505.16245v2 |
are as follows, "belt", "brick", "broom", "bucket", "candle", "clock", "comb", "knife", "lamp", "pencil", "pillow", "purse", "rope", "sock", "table" Creative Writing Task (CWT). The three-word sets used in evaluating the model are as follows, ("stamp, letter, send"), ("petrol, diesel, pump"), ("statement, stealth, dete... | https://arxiv.org/abs/2505.16245v2 |
by a skewed pro- portion of longer preference pairs, which may inad- vertently bias the model toward generating longer responses. E Results with Standard Deviation In this section, we report the results with the stan- dard deviation values in Table E.1.F∆DD-based Evaluation Similar to the results presented fig. 1 for O... | https://arxiv.org/abs/2505.16245v2 |
PGT Unique Occupations 0.1900 0 .1900 0 .1900 0.2000 AUT DSI 0.8943±0.02 0.8960±0.02 0.8974±0.02 0.8970±0.02 CWT DSI 0.8557±0.01 0.8555±0.01 0.8616±0.01 0.8614±0.01 CWT ArmoRM Score 0.1571±0.01 0.1589±0.01 0.1585±0.01 0.1590±0.01 CWT 4-gram div. POS 0.5210 0.5229 0.5080 0.4960 CWT 4-gram div. 3.0820 3.0770 3.095 3.1070... | https://arxiv.org/abs/2505.16245v2 |
Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models Hwiyeong Lee, Uiji Hwang, Hyelim Lim, Taeuk Kim* Hanyang University, Seoul, Republic of Korea {hyglee,willpower,yomilimi,kimtaeuk}@hanyang.ac.kr Abstract Large language models often ret... | https://arxiv.org/abs/2505.16252v1 |
without establishing whether the identified regions play a causal role. As a result, the underlying connection between localization and knowledge unlearning remains unexplored. In this paper, we investigate whether the success of localization truly translates into improved un- learning, particularly by leveraging a con... | https://arxiv.org/abs/2505.16252v1 |
investi- gation into localization for knowledge unlearning attributes factual knowledge to a specific set of value vectors and designates them as the target components for localization, allowing us to probe whether localization offers a viable path forward for addressing this challenge. 3 Revisiting Localized Unlearnin... | https://arxiv.org/abs/2505.16252v1 |
This de- sign ensures a fair comparison across methods by standardizing the retention level to a tolerable de- gree of degradation. Second, to evaluate whether unlearning methods consistently guide the model toward more desirable parameter updates through- out the process, we compute the area under the FS–RS curve, ref... | https://arxiv.org/abs/2505.16252v1 |
0.64 MU95 ↑-10.33 -10.00 0.86 0.46 -13.88 -13.77 0.23 0.56 NPOAUES ↑0.625 0.619 0.011 0.71 0.638 0.639 0.007 0.52 MU95 ↑-9.45 -8.56 0.90 0.31 -14.19 -14.33 0.14 0.72 DPOAUES ↑0.497 0.492 0.007 0.66 0.561 0.568 0.010 0.36 MU95 ↑-13.26 -13.60 1.09 0.68 -13.62 -13.52 0.41 0.57 RMUAUES ↑0.506 0.502 0.017 0.37 0.437 0.439 0... | https://arxiv.org/abs/2505.16252v1 |
directly supervises parameter up- dates: instead of relying on output-level signals, we minimize the L2 distance between the MLP outputs at each layer and those produced by θr. The results shown in Figure 1 are surprising: even when adjust- ingVrdm, the MLP outputs of θrcan be reproduced to a degree comparable to Vtgt.... | https://arxiv.org/abs/2505.16252v1 |
unlearning methods. Artificial Intelligence Review , 58(3):90. Kent Chang, Mackenzie Cramer, Sandeep Soni, and David Bamman. 2023. Speak, memory: An archaeol- ogy of books known to ChatGPT/GPT-4. In Proceed- ings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages 7312–7327, Singapore. As... | https://arxiv.org/abs/2505.16252v1 |
Wagle: Strategic weight attribution for effective and modular unlearning in large language models. arXiv preprint arXiv:2410.17509 . Nathaniel Li, Alexander Pan, Anjali Gopal, Sum- mer Yue, Daniel Berrios, Alice Gatti, Justin D. Li, Ann-Kathrin Dombrowski, Shashwat Goel, Gabriel Mukobi, Nathan Helm-Burger, Rassin Labab... | https://arxiv.org/abs/2505.16252v1 |
Han, and Kilian Q Weinberger. 2025b. Re- thinking LLM unlearning objectives: A gradient per- spective and go beyond. In The Thirteenth Interna- tional Conference on Learning Representations . Jingwen Ye, Yifang Fu, Jie Song, Xingyi Yang, Songhua Liu, Xin Jin, Mingli Song, and Xinchao Wang. 2022. Learning with reco... | https://arxiv.org/abs/2505.16252v1 |
required to recover the suffix. Formally, ES(x, y;θ) = 1−1 |y|min k{k|f([x, y<k];θ) =y≥k}, where fdenotes the model’s output, xis the input, and yis the target output, with y<kandy≥k representing the prefix and suffix of ysplit at position k. Accordingly, Forget Strength (FS) captures the reduction in ES on the forget ... | https://arxiv.org/abs/2505.16252v1 |
vector. Formally, the attribution score Aℓ(i)is defined as the average over the suffix length Tof the product between the absolute activation coefficient and the norm of the corresponding value vector: Aℓ(i) =1 TTX t=1 hℓ i,t vℓ i , where hℓ i,tdenotes the activation coefficient of the i-th value vector at layer ℓat ti... | https://arxiv.org/abs/2505.16252v1 |
permutations in which the permuted difference equals or exceeds the observed one. A small p-value (e.g., p <0.05) indicates that the observed AUES difference is unlikely to have occurred by chance, thus providing evidence against the null hypothesis. MU95 bootstrap test The null hypothesis ( H0) is that there is no sig... | https://arxiv.org/abs/2505.16252v1 |
arXiv:2505.16258v1 [cs.CL] 22 May 2025IRONIC : Coherence-Aware Reasoning Chains for Multi-Modal Sarcasm Detection Aashish Anantha Ramakrishnan1*, Aadarsh Anantha Ramakrishnan2*, Dongwon Lee1 1The Pennsylvania State University;2National Institute of Technology, Tiruchirappalli 1{aza6352, dul13}@psu.edu,2106121001@nitt.e... | https://arxiv.org/abs/2505.16258v1 |
OpenAI et al., 2024). Our findings on two different datasets: MMSD2.0 (Qin et al., 2023) and RedEval (Tang et al., 2024) show that the higher- order reasoning abilities of MLLMs play a crucial role in how they leverage CRs. IRONIC enables more pragmatically-aware models such as GPT- 4o (OpenAI et al., 2024) to achieve ... | https://arxiv.org/abs/2505.16258v1 |
as shown in Figure 1, constructs a reasoning chain with 2 main components: (1) Relation Extraction (2) Interpre- tative Reasoning. The predicted CR distributions and specific prompts are shown in the Appendix Sections A & C. 3.1 Relation Extraction The Relation Extraction step analyzes each image- text pair and predict... | https://arxiv.org/abs/2505.16258v1 |
subreddits. 4.2 Evaluation Metrics To measure the performance of MLLMs on multi- modal sarcasm detection, we use the F1 score (weighted) as our main metric since it is framed as a binary classification task. We also report overall Accuracy, Precision, and Recall for all models. 3 Dataset Model Type Accuracy ↑ Precision... | https://arxiv.org/abs/2505.16258v1 |
that larger proprietary models may demon- strate higher internal reasoning fidelity to make use of cognitive reasoning scaffolds such as CRs. 6 Conclusion We propose IRONIC , a coherence-aware in- context prompting strategy inspired by the The- ory of Discourse Coherence for multi-modal sar- casm detection. Our study c... | https://arxiv.org/abs/2505.16258v1 |
text-to- image synthesis with filtered news captions. In The Third Workshop on Advances in Language and Vision Research . Association for Computational Linguistics. Yitao Cai, Huiyu Cai, and Xiaojun Wan. 2019. Multi- modal sarcasm detection in twitter with hierarchical fusion model. In Proceedings of the 57th Annual Me... | https://arxiv.org/abs/2505.16258v1 |
for multi-modal sarcasm de- tection. In Findings of the Association for Computa- tional Linguistics: EMNLP 2020 , pages 1383–1392, Stroudsburg, PA, USA. Association for Computa- tional Linguistics. Bo Pang and Lillian Lee. 2008. Opinion mining and sentiment analysis. Found. Trends ®Inf. Retr. , 2(1- 2):1–135. Libo Qin,... | https://arxiv.org/abs/2505.16258v1 |
and Jinlong Li. 2021. Modeling incongruity between modalities for multimodal sarcasm detection. IEEE Multimed. , 28(2):86–95. Chunpu Xu, Hanzhuo Tan, Jing Li, and Piji Li. 2022. Understanding social media cross-modality discourse in linguistic space. In Findings of the Association for Computational Linguistics: EMNLP 2... | https://arxiv.org/abs/2505.16258v1 |
and were able to get results. 1https://github.com/vllm-project/vllm 8 System Message for Baseline Zero-Shot/CoT Evaluation You are an expert linguist. Your task is to analyze a image-text pair and determine if it is ’sarcastic’ or ’non-sarcastic’. System Message for IRONIC You are an expert linguist, and your task is t... | https://arxiv.org/abs/2505.16258v1 |
arXiv:2505.16263v1 [cs.CR] 22 May 2025All You Need is "Leet": Evading Hate-speech Detection AI Sampanna Yashwant Kahu∗ sampanna@vt.edu Virginia Tech Blacksburg, VirginiaNaman Ahuja∗ namanahuja@vt.edu Virginia Tech Blacksburg, Virginia ABSTRACT Social media and online forums are increasingly becoming popular. Unfortunat... | https://arxiv.org/abs/2505.16263v1 |
aim of this research project is to design black-box techniques to protect users from hate-speech on online platforms by generating perturbations that can fool state of the art deep learning based hate speech detection models, hence decreasing their efficiency. We also want to ensure minimum change in the original meani... | https://arxiv.org/abs/2505.16263v1 |
presented in four papers to set up an experimental comparative analysis of state-of-the-art hate speech detection models and datasets (Wikipedia and Twitter). They also presented several attacks: word changes, word-boundary changes, and appending unrelated innocuous words which proved to be effective against all models... | https://arxiv.org/abs/2505.16263v1 |
online social media platforms since these are the primary targets for attackers and often employ hate speech detection models for curbing hate speech. 2.2 Dataset description and analysis We used the hate speech dataset by Mondal et al [ 15]. This dataset contains total 20,705 posts from Twitter collected in 2014-2015.... | https://arxiv.org/abs/2505.16263v1 |
pass in a text string within 3000 bytes to the API using an HTTP POST request and the response will contain the overall toxicity score of the text string that was passed in the input request. Further, the HTTP API also supports a span annotation feature. This feature returns a sentence level toxicity of the input text.... | https://arxiv.org/abs/2505.16263v1 |
of every word. For example, a sentence like: The quick brown fox jumped over the fence. was changed to: The. Quick. Brown. Fox. Jumped. Over. The. Fence. However, upon manually inspecting the results we observed that what appeared to be the most toxic word often did not have the highest toxicity scores. One possible ex... | https://arxiv.org/abs/2505.16263v1 |
is less than 4 characters: Do not perturb the word. –Length of the word is an even number: Interchange the middle two characters in the word. For example hate would become htae. –Length of the word is an odd number: Interchange the two characters surrounding the middle character. For example walks would become wklas . ... | https://arxiv.org/abs/2505.16263v1 |
HateSonar.•Modified category shift score: This metric is only applica- ble for Perspective API since it is possible that Perspective API sometimes would not return the toxicity value (See sec- tion 2.3.4) for a given input text. Thus, modified shift score is defined as the percent of total examples in the dataset that ... | https://arxiv.org/abs/2505.16263v1 |
alphabet, Greek alphabet, Latin alphabet, etc). Thus, if there exists an inverse dictionary to map from these Unicode characters to the regular English alphabet, then the during prediction time, the input string can be sanitized to replace all Unicode alphabets available in the inverse dictionary with the regular Engli... | https://arxiv.org/abs/2505.16263v1 |
based on finding the most toxic words(s), we use the dictionary created using the Perspective API to find the candidate words. But, we still feel that even with this limitation, the design gives us a fair idea of the performance of various perturbations across models. 6 CONCLUSION We came up with 3 classes of perturbat... | https://arxiv.org/abs/2505.16263v1 |
Original and resulting toxicities for Leet speak per- turbation for Perspective API Figure 10: Original and resulting toxicities for Leet speak perturbation for HateSonar 7 Figure 11: Original and resulting toxicities for Typo pertur- bation for Perspective API Figure 12: Original and resulting toxicities for Typo pert... | https://arxiv.org/abs/2505.16263v1 |
arXiv:2505.16270v1 [cs.CL] 22 May 2025Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning Jiaru Zou1, Yikun Ban1†, Zihao Li1, Yunzhe Qi1, Ruizhong Qiu1, Ling Yang2, Jingrui He1† 1University of Illinois Urbana-Champaign,2Princeton University jiaruz2@illinois.edu Abstract Large language models are typic... | https://arxiv.org/abs/2505.16270v1 |
expected loss over fine-tuning datasets [ 81,96]. We take a deeper step to systematically record the rich intermediate information within the model, including input data (Question), internal hidden state representations (Rationale), and token-level quantified errors (Mistakes), as Mistake Log components to track model’... | https://arxiv.org/abs/2505.16270v1 |
pass through the residual stream of the model, letLPbe the total number of decoder layers in the Pilot model. For each layer l∈[LP], we define ht,i,l(eXt;θP t−1)as the (decoder) hidden representations of the i-th token. After the final decoder layer, the Pilot model outputs logits over the vocabulary V, conditioned on ... | https://arxiv.org/abs/2505.16270v1 |
for Transformer Copilot. Recall that the goal of SFT is to optimize θPby minimizing the expected loss E(Xt,Yt)∼D LP t . While this process adjusts model parameters using gradient descent, it treats each error as a transient signal, consumed and discarded immediately after the parameter update. As a result, the final ... | https://arxiv.org/abs/2505.16270v1 |
eXtandhtfrom MT), we propose a modified cross-attention mechanism in each layer of the Copilot, defined as: NewQ=HC l−1·WQ,forl= 1, ..., LC, NewK=Concat eXt,Pool LP ht(eXt;θP t−1) ·WK, NewV=Concat eXt,Pool LP ht(eXt;θP t−1) ·WV,(6) where Pool LP(·)denotes the mean pooling across LPlayers of the Pilot and Concat( ... | https://arxiv.org/abs/2505.16270v1 |
states for the preceding tokens. We adopt the RMSE loss to prevent the distribution error from being further diminished by the square operation, avoiding the over-smoothing effect that squaring may introduce in the gradient signal during backpropagation. Next, we show how to jointly train the Pilot model fPand the Copi... | https://arxiv.org/abs/2505.16270v1 |
optionally terminate upon generation of the [EOS] (end-of-sequence) token. 4 Analyses - Why Learn from the Mistake Log? To elucidate the roles of the Mistake Log and Copilot model in enhancing the Pilot model’s inference- time performance, we present both theoretical and empirical analyses in this section. Theoretical ... | https://arxiv.org/abs/2505.16270v1 |
Top -Token Prediction per Layer (Logits Lens) Top -Token Prediction per Layer (Logits Lens)Copilot ModelFigure 4: Example of Copilot’s Token-level Rectification on SIQA. The token-level formatting error (‘forgot’) originates during the Pilot’s mid-way generation and is corrected (‘answer’) by incorporating the Copilot.... | https://arxiv.org/abs/2505.16270v1 |
are provided in Appendix F.3. 5.1 Incorporating T-Copilot into Pilot Models Yields Better Performance Effectiveness of Copilot in Enhancing Pilot. Table 1 presents the performance gains of incorporating T-Copilot into the Pilot models across different model scales and types. T-Copilot consistently 7 Table 1: Experiment... | https://arxiv.org/abs/2505.16270v1 |
Qwen2.5-14B 14B 91.8 85.6 94.3 75.2 84.5 93.1 87.4 63.5 79.5 92.4 87.9 80.8 Qwen2.5-7B + T-Copilot-3B 10B (-4B) 92.5 87.2 95.3 74.8 84.3 94.9 88.2 64.2 79.7 94.8 88.1 81.7 Comparison with Layer/Adapter Expansion Baselines Mistral-Pro-8B 8B 83.1 81.9 86.1 70.8 76.1 80.6 79.8 35.5 54.4 88.2 68.5 61.7 LLaMA-Pro-8B 8B 88.4... | https://arxiv.org/abs/2505.16270v1 |
Ablation Studies. Detailed ablation studies on T-Copilot, including model design choices, input insertion patterns, and the effect of the hyperparameter λ, are presented in Appendix G.6. 6 Related Works LLMs Supervised Fine-tuning. Supervised fine-tuning (SFT) serves as the standard post-training method for specializin... | https://arxiv.org/abs/2505.16270v1 |
Jian Kang, Hanghang Tong, and Jingrui He. Pagerank bandits for link prediction. In A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang, editors, Advances in Neural Information Processing Systems , volume 37, pages 21342–21376. Curran Associates, Inc., 2024. [8]Nora Belrose, Zach Furman, Lo... | https://arxiv.org/abs/2505.16270v1 |
arXiv preprint arXiv:2012.14913 , 2020. [26] Charles Goddard, Shamane Siriwardhana, Malikeh Ehghaghi, Luke Meyers, Vlad Karpukhin, Brian Benedict, Mark McQuade, and Jacob Solawetz. Arcee’s mergekit: A toolkit for merging large language models. arXiv preprint arXiv:2403.13257 , 2024. [27] Caglar Gulcehre, Tom Le Paine, ... | https://arxiv.org/abs/2505.16270v1 |
Rik Koncel-Kedziorski, Subhro Roy, Aida Amini, Nate Kushman, and Hannaneh Hajishirzi. Mawps: A math word problem repository. In Proceedings of the 2016 conference of the north american chapter of the association for computational linguistics: human language technologies , pages 1152–1157, 2016. [44] Hector Levesque, Er... | https://arxiv.org/abs/2505.16270v1 |
Ahtsham Zafar, Aafaq Khan, and Arsalan Shahid. The ultimate guide to fine-tuning llms from basics to breakthroughs: An exhaustive review of technologies, research, best practices, applied research challenges and opportunities. arXiv preprint arXiv:2408.13296 , 2024. [61] Arkil Patel, Satwik Bhattamishra, and Navin Goya... | https://arxiv.org/abs/2505.16270v1 |
arXiv preprint arXiv:2408.00118 , 2024. [77] Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 , 2023. [78] A Vaswani. Att... | https://arxiv.org/abs/2505.16270v1 |
tuning for large language models: A survey. arXiv preprint arXiv:2308.10792 , 2023. [94] Zihao Zhao, Eric Wallace, Shi Feng, Dan Klein, and Sameer Singh. Calibrate before use: Improving few-shot performance of language models. In International conference on machine learning , pages 12697–12706. PMLR, 2021. [95] Jiawei ... | https://arxiv.org/abs/2505.16270v1 |
Baseline Comparison . . . . . . . . . . . . . . . . . . . . . . 28 G.2 Downstream Recommendation Evaluation . . . . . . . . . . . . . . . . . . . . . . 28 G.3 Transferability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 G.4 Scalability . . . . . . . . . . . . . . . . . . . . . . . . . . ... | https://arxiv.org/abs/2505.16270v1 |
Transformer [ 78]. However, our model design exhibits several key advantages compared to the standard decoder module: Specifically, our Copilot model (i) eliminates the need for positional embeddings to preprocess input sequences, (ii) does not require a softmax layer to normalize high- dimensional logits distributions... | https://arxiv.org/abs/2505.16270v1 |
(pt,i[k]−ept,i[k])2 fC t,<i,ˆyt,<ii <EθP∼AP (Xt,Yt)∼D (pt,i[k]−ˆpt,i[k])2 ˆyt,<i . Proof. For brevity, we omit the explicit expectation condition over the Pilot model’s previously generated tokens ˆyt,<i, the Copilot model’s preceding outputs fC t,<i, and the dimension index [k]in the following proof. Firstly, by the... | https://arxiv.org/abs/2505.16270v1 |
two reasoning tasks, including SIQA [ 71] and MAWPS [ 43]. The dataset details are provided later in Appendix E. Example of Copilot’s Token-level Rectification. Figure 6 demonstrates another representative example of Copilot’s token-level rectification on the factual error made by the Pilot model. The token “10" is ori... | https://arxiv.org/abs/2505.16270v1 |
[ 85] to avoid any potential training data leakage. Each aforementioned dataset’s individual test set is used for evaluation. Note that , unlike commonsense reasoning, fine- tuning for arithmetic reasoning involves labels with zero-shot Chain-of-Thought (CoT) [ 42] prompts. Consequently, the training cutoff length is l... | https://arxiv.org/abs/2505.16270v1 |
0.875 of a lap and then took a break by jogging 0.75 of a lap. How much farther did Darnel sprint than jog? Answer: Step 1: Find the total distance Darnel covered. Total distance = distance sprinted + distance jogged Total distance = 0.875 + 0.75 = 1.625 laps Step 2: Find the distance Darnel sprinted. Distance sprinted... | https://arxiv.org/abs/2505.16270v1 |
F Experiment Setups F.1 Hyperparameters and Training/Inference Details Tables 4-9 present our hyperparameter settings of each task for reproducibility. We perform hyperpa- rameter tuning for both T-Copilot and baseline methods. Unless otherwise specified, both our method and baseline implementations use beam search dec... | https://arxiv.org/abs/2505.16270v1 |
256 256 256 Maximum Learning Rate 1e−31e−31e−33e−3 Learning Rate Scheduler Cosine Cosine Cosine Cosine Optimizer AdamW AdamW AdamW AdamW Warmup Ratio 0.05 0.05 0.05 0.05 Weight Decay 0.01 0.01 0.01 0.01 Drop Out 0.1 0.1 0.1 0.1 Inference Configurations Temperature 0.1 Top p 0.95 Top k 40 Num Beams 4 Maximum New Tokens ... | https://arxiv.org/abs/2505.16270v1 |
for our method, we exclude the conventional positional embedding mechanism and omit the softmax layer typically used for normalizing logits 26 into probability distributions. Additionally, we add a linear layer to map the Copilot inputs from the logits distribution dimension to the decoder hidden state dimension. If th... | https://arxiv.org/abs/2505.16270v1 |
LLaMA-2-13B . (iii) MoE Models: For the Mixture-of-Expert based models, we use Mistral-7B with version Mistral-7B-v0.3 andMinistral-8B with version Ministral-8B-Instruct-2410 . Layer/Adapter Expansion Models. In our experiments, we also compare against baseline methods that utilize layer and adapter expansion approache... | https://arxiv.org/abs/2505.16270v1 |
9B 86.2 86.8 93.5 71.8 82.7 83.2 84.0 38.9 66.1 90.8 75.4 67.8 Qwen2.5-7B + T-Copilot-3B 10B 92.5 87.2 95.3 74.8 84.3 94.9 88.2 64.2 79.7 94.8 88.1 81.7 Table 11 shows the full comparison results of T-Copilot against baseline models and methods with matched and larger parameter scales. Notably, under the same model arc... | https://arxiv.org/abs/2505.16270v1 |
using 30M and 126M fewer parameters. These results demonstrate that the error-correction capabilities of T-Copilot are not confined to reasoning tasks but also generalize effectively to other application domains, such as recommendation, where precise LLM decision- making is critical for downstream utility. G.3 Transfer... | https://arxiv.org/abs/2505.16270v1 |
increases the inference latency by less than 2% relative to the original Pilot models, while yielding significant performance gains. 30 Table 15: Efficiency Comparison on Inference Latency. We report the total response time (s) per instance across six commonsense reasoning datasets, along with the average result. Infer... | https://arxiv.org/abs/2505.16270v1 |
Decoder-only Copilot model accordingly. The design options are listed below: •Pattern 1 (Ours): Collect the hidden states across all Pilot model layers LPand insert them as key-value (KV) inputs for the even-numbered layers of the Copilot model. •Pattern 2: Collect the hidden states across all Pilot model layers LPand ... | https://arxiv.org/abs/2505.16270v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.