text string | source string |
|---|---|
these two heuristics were labeled as degeneration cases and added to the degeneration dataset. For each such case, we attempted to construct a sanitized version by removing the degenerated outputs and recomputing statistics if enough clean outputs remained. When all outputs were degenerated (e.g., all reached the 15,00... | https://arxiv.org/abs/2505.16881v1 |
the base prompt model string LLM used for generation dataset string Name of the dataset the prompt comes from prompt_text string Raw text of the prompt longest_response string Longest response from the batch shortest_response string Shortest response from the batch input_size int Number of input tokens output_sizes Lis... | https://arxiv.org/abs/2505.16881v1 |
Don’t “Overthink” Passage Reranking: Is Reasoning Truly Necessary? Nour Jedidi1Yung-Sung Chuang2James Glass2Jimmy Lin3 1MIT Lincoln Laboratory2Massachusetts Institute of Technology3University of Waterloo nour.jedidi@ll.mit.edu Abstract With the growing success of reasoning mod- els across complex natural language tasks... | https://arxiv.org/abs/2505.16886v1 |
disabling the reasoning pro- cess of a reasoning reranker affect its rerank- ing accuracy? To answer these research questions, we train and evaluate three reranker variants: (1) StandardRR , a standard LLM-based pointwise reranker that di- rectly classifies query-passage pairs as relevant or non-relevant (Nogueira et a... | https://arxiv.org/abs/2505.16886v1 |
for a given query-passage pair. To train StandardRR, the simplest approach is to directly fine-tune an LLM to produce the tokens “true” or “false” given a dataset of (query, passage, relevance label) triples, where “true” and “false” denote rele- vant or not relevant, respectively. At inference, for each query-passage ... | https://arxiv.org/abs/2505.16886v1 |
69.4 51.4 45.5 ReasonRR 70.4 66.4 65.9 45.2 41.3 + Qwen2.5-7B StandardRR 74.6 70.0 70.9 50.3 46.3 ReasonRR 70.3 64.3 65.9 45.6 41.1 Table 1: In-domain performance of StandardRR versus ReasonRR. Each Qwen2.5 model reranks the top-100 passages from BM25. R1’s final relevance predictions. The dataset con- sists of approxi... | https://arxiv.org/abs/2505.16886v1 |
a similar story: StandardRR outperforms ReasonRR, achieving 3.4, 1, and 3.2 points higher average NDCG@10 across the 1.5B, 3B, and 7B model sizes. However, while in-domain StandardRR al- ways outperformed ReasonRR, out-of-domain, the results suggest that reasoning canbe beneficial depending on the model scale and domai... | https://arxiv.org/abs/2505.16886v1 |
ReasonRR-NoReason is less effective for smaller models (1.5B and 3B), but as model size increases, ReasonRR-NoReason begins outperform ReasonRR. In fact, at the 7B scale, ReasonRR-NoReason is able to improve by 3 points versus ReasonRR on BRIGHT, closing the gap between StandardRR and ReasonRR. These findings are remar... | https://arxiv.org/abs/2505.16886v1 |
ReasonRR (in terms of F1 and precision), yet outperforms it in terms of retrieval metrics, as discussed in Section 3.2. Over the next two subsections, we provide potential ex- planations for this observation. 5 Figure 2: Relevance Scores Distribution across Qwen2.5-7B reranker variants on DL19. 4.2 Relevance Scores Dis... | https://arxiv.org/abs/2505.16886v1 |
ReasonRR-NoReason is more ef- fective in reranking, it would appear that (2) is the more crucial factor for reranking accuracy, high- lighting the importance of partial relevance model- ing for pointwise rerankers. Can injecting a concept of partial relevance into ReasonRR help? We explore a simple method to incorporat... | https://arxiv.org/abs/2505.16886v1 |
improves by 1.8 points on MS MARCO and 2.9 points on BRIGHT, even though the relevance classification metrics presented in Table 4, particularly precision, is gen- erally on-par with ReasonRR.So, is reasoning truly necessary for pointwise rerankers? Even with the improvements from ReasonRR + Self-Consistency, ReasonRR ... | https://arxiv.org/abs/2505.16886v1 |
as summarized in Sui et al. (2025), has focused on fine-tuning LLMs to reason more efficiently by leveraging variable length chain-of- thought data (Munkhbat et al., 2025; Xia et al., 2025; Yu et al., 2024; Kang et al., 2025). We highlight that rather than trying to make reason- ing models more efficient, our work is p... | https://arxiv.org/abs/2505.16886v1 |
Rea- sonRR + Self-Consistency — which was grounded in observations from our analysis — makes strong improvements on ReasonRR, it still is less effective than our StandardRR. While we propose potential solutions to improve ReasonRR, we leave the im- plementation of these methods as future work. We hope our results and a... | https://arxiv.org/abs/2505.16886v1 |
Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. Deepseek-r1: In- centivizing reasoning capability in llms via reinforce- ment learning. arXiv preprint arXiv:2501.12948 . Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-ran... | https://arxiv.org/abs/2505.16886v1 |
efficient rea- soning for large language models. arXiv preprint arXiv:2503.16419 . Weiwei Sun, Lingyong Yan, Xinyu Ma, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, and Zhaochun Ren. 2023. Is chatgpt good at search? investigating large language models as re-ranking agents. In Proceedings of the 2023 Conference ... | https://arxiv.org/abs/2505.16886v1 |
cense Agreement. •Qwen2.5-7B is under the Apache 2.0 License.MS MARCO v1 MS MARCO v2 DL19 DL20 DL21 DL22 DL23 BM25 50.6 48.0 44.6 26.9 26.3 + Qwen2.5-1.5B StandardRR 73.1 69.4 68.9 50.7 44.2 ReasonRR 68.7 63.1 65.7 43.3 38.8 ReasonRR-NoReason 69.9 61.7 67.3 44.9 39.5 + Qwen2.5-3B StandardRR 72.5 68.9 69.4 51.4 45.5 Rea... | https://arxiv.org/abs/2505.16886v1 |
19.9 22.6 31.0 12.7 30.8 6.8 26.0 38.2 27.5 + Rank1-7B (Reported Results) 48.8 36.7 20.8 35.0 22.0 18.7 36.2 12.7 31.2 6.3 23.7 37.8 27.5 Table 9: Full results for StandardRR, ReasonRR, ReasonRR-NoReason, and ReasonRR + Self-Consistency. All models rerank the top-100 passages from BM25 + GPT-4 CoT . MS MARCO BRIGHT Sta... | https://arxiv.org/abs/2505.16886v1 |
arXiv:2505.16888v1 [cs.CR] 22 May 2025CAIN : Hijacking LLM-Humans Conversations via a Two-Stage Malicious System Prompt Generation and Refining Framework Viet Pham Independent Researcher viethungpham0304@gmail.comThai Le Indiana University tle@iu.edu Abstract Large language models (LLMs) have advanced many applications... | https://arxiv.org/abs/2505.16888v1 |
(2023). In this work, we identify and investigate a new class of security threat to LLMs: targeted input manipulation, in which LLMs are manipulated via malicious system prompts to remotely hijack AI-humans’ conversations by inducing incorrect or harmful responses to specific, targeted ques- 1 tions while maintaining c... | https://arxiv.org/abs/2505.16888v1 |
2024), AutoDAN (Zhu et al., 2024), ECLIPSE (Jiang et al., 2025), GASP (Basani and Zhang, 2024), COLD- Attack (Guo et al., 2024; Qin et al., 2022). Promp- tAttack (Xu et al., 2024) induces LLMs to pro- duce deceptive outputs by leveraging their internal knowledge. GCQ (Hayase et al., 2024) employs a best-first-search al... | https://arxiv.org/abs/2505.16888v1 |
for each target question using GPT-4o, ensuring the attack generalizes across paraphrases. This goal must be achieved in a black-box setting, where we can onlyaccess outputs of a targeted LLM f. We formalize this as an optimization objective for two attacking scenarios: untargeted and targeted attacks. Untargeted Attac... | https://arxiv.org/abs/2505.16888v1 |
to ana- lyze performance failures and generate insights for improving prompt quality. Prompt Generator iteratively generates a new prompt using the history of previously generatedAlgorithm 1 Adversarial Prompt Optimization 1:Input: A hand-crated system prompt p0, maximum # perturbed words max _perturbs , Qt={q, y}, and... | https://arxiv.org/abs/2505.16888v1 |
to the next iteration. This ensures that all perturbations enhance adversarial effectiveness without significantly degrading per- formance on benign examples (Alg. 1, Ln. 16). For the stopping criteria, we evaluate at each it- eration whether a maximum allowable number of perturbed words is reached or whether the attac... | https://arxiv.org/abs/2505.16888v1 |
Benign Malicious Difference F1↑EM↑F1↓ EM↓∆F1↑∆EM↑Llama2-7BNSP 66.48 56.10 61.00 61.00 5.48 -4.90 Manual 73.09 68.90 54.00 54.00 19.09 14.90 AAP 66.31 58.88 79.19 73.23 -12.88 -14.35 CAIN 63.84 56.14 33.36 28.20 30.48 27.94Llama2-13BNSP 76.29 67.70 97.10 95.00 -20.81 -27.30 Manual 85.00 82.60 96.50 94.00 -11.50 -11.40 A... | https://arxiv.org/abs/2505.16888v1 |
Four options (A, B, C or D), and (3) Free-form text (no explicit choices are provided). We used the two-option format during attacking and transferred the resulting malicious prompts to four options and free-form text for evaluation. Figure A1 illustrates the input format for two options. 6.2 Results We report results ... | https://arxiv.org/abs/2505.16888v1 |
success and benign robustness in targeted attacks across different prompting formats. 7 Discussion Affects of Optimization Threshold k.We inves- tigate the trade-offs between benign performance and synthetic target when adjusting the number of incorrect target thresholds k∈[1..11](Alg. 1, Ln.. 17). As shown in Figure 4... | https://arxiv.org/abs/2505.16888v1 |
of our security threat in practice. Potential Defense. Our findings suggest that tradi- tional defenses, such as detecting lexical similarity between prompts and target questions or using a perplexity-based filtering (Jain et al., 2023) are in- sufficient to defend against CAIN . Table 4 shows that the optimized prompt... | https://arxiv.org/abs/2505.16888v1 |
596. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El-Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, and 12 others. 2022. Training a h... | https://arxiv.org/abs/2505.16888v1 |
Aniruddha Saha, Jonas Geiping, and Tom Goldstein. 2023. Baseline defenses for ad- versarial attacks against aligned language models. Preprint , arXiv:2309.00614. Weipeng Jiang, Zhenting Wang, Juan Zhai, Shiqing Ma, Zhengyu Zhao, and Chao Shen. 2025. An optimiz- able suffix is worth a thousand templates: Efficient black... | https://arxiv.org/abs/2505.16888v1 |
35:15109. Hugo Touvron, Louis Martin, Kevin Stone, Peter Al- bert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian CantonFerrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, and 49 oth- ers. 2023.... | https://arxiv.org/abs/2505.16888v1 |
the same range of k. This trend indicates that while the attack more effectively degrades performance on malicious queries at higher k values, this also comes with a slight decrease in performance on benign questions compared to their corresponding initial attacked state and a more noticeable reduc- tion compared to th... | https://arxiv.org/abs/2505.16888v1 |
Pythia models, respectively. on Pythia), demonstrating CAIN ’s superior abil- ity to selectively degrade targeted outputs without broadly compromising accuracy. A.5 Additional results for targeted attacks Table A4 shows that AAP achieves the best per- formance in the two-option setting ( ΨF1 = 50.94, ΨEM = 42.58), but ... | https://arxiv.org/abs/2505.16888v1 |
Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs Zeyu Wei1,2[0009−0001−3335−2366], Shuo Wang1,2[0009−0008−4232−4245], Xiaohui Rong1[0009−0001−0536−4538], Xuemin Liu1[0009−0007−8759−1219] (B), and He Li1,2[0009−0004−3862−9936] 1Computer Network Informati... | https://arxiv.org/abs/2505.16894v1 |
Results show that injected contexts form an "attention shadow," gradually shifting model focus, causing representation drift, and ultimately generating incorrect answers. This study doesn’t propose new models but identifies and characterizes representation drift patterns related to hallucinations, providing empirical e... | https://arxiv.org/abs/2505.16894v1 |
crel idenotes the i-th injected relevant fragment. Symmetrically, the irrelevant track furnishes potentially misleading snippets for the same question, Cirr={cirr 1, cirr 2, ..., cirr n} (2) with cirr irepresenting the i-th injected irrelevant fragment. Under both con- ditions, each question undergoes 15 rounds of prog... | https://arxiv.org/abs/2505.16894v1 |
=1 NNX i=11 |S(yi)|X s∈S(yi)H(s,Ri) (9) where S(yi)denotes the set of individual sentences comprising the answer yi. This metric quantifies the average hallucination likelihood at the sentence level and helps determine whether hallucinations are localized to specific sentences or dispersed throughout the output. To lin... | https://arxiv.org/abs/2505.16894v1 |
element between two distribu- tions and nis the distribution length. Zero-padding is again applied to maintain consistent dimensionality. The Spearman coefficient ρ∈[−1,1], where negative values indicate rank inversion and positive values denote alignment. Unlike di- vergence measures, Spearman correlation focuses excl... | https://arxiv.org/abs/2505.16894v1 |
false content, resulting in highly concentrated hallucinations. Rele- vant information provided some factual support, with hallucinations appearing only as local deviations; accumulated irrelevant information caused models to immerse in self-constructed erroneous contexts, producing concentrated misin- formation.(See F... | https://arxiv.org/abs/2505.16894v1 |
50.0379 0.0248 0.1176 0.0846 0.8212 0.8119 0.8800 1.0000 0.6206 0.5278 70.0318 0.0186 0.0996 0.0666 0.8228 0.8119 0.8800 1.0000 0.6174 0.4945 90.0256 0.0151 0.0816 0.0553 0.8228 0.8119 0.9000 1.0000 0.6095 0.4980 11 0.0214 0.0127 0.0712 0.0467 0.8228 0.8119 0.9000 1.0000 0.6164 0.4935 15 0.0158 0.0092 0.0539 0.0339 0.8... | https://arxiv.org/abs/2505.16894v1 |
irrele- vant contexts. For example, in round 15 of the Llama-3 8B model, Cos-Drift reached 0.2116 under relevant context versus 0.1977 under irrelevant context; Ent-Drift was 1.4643 under relevant context compared to 1.1347 under irrele- vant context. Under irrelevant context conditions, JS-Drift and Spearman-Drift sta... | https://arxiv.org/abs/2505.16894v1 |
as tangential responses or topic deviations, but with lower internal consis- tency. Observations indicate that under relevant context conditions, Cos-Drift and Ent-Drift variances are generally higher than under irrelevant contexts, while JS-Drift and Spearman-Drift variances remain relatively similar across both con- ... | https://arxiv.org/abs/2505.16894v1 |
exists between semantic as- similation and attention divergence; when models cannot deeply assimilate con- text, they sacrifice attention focus to expand retrieval range, thus increasing the probability of concatenation-type hallucinations. Small models with insufficient assimilation capacity compensate for com- prehen... | https://arxiv.org/abs/2505.16894v1 |
Filippova, K.: Controlled hallucinations: Learning to generate faithfully from noisy data. In: Findings of the Association for Computational Linguistics: EMNLP 2020. pp. 864–870. Online (Nov 2020) 13. Flemings, J., Zhang, W., Jiang, B., et al.: Characterizing context influence and hallucination in summarization. arXiv ... | https://arxiv.org/abs/2505.16894v1 |
UNCLE: Uncertainty Expressions in Long-Form Generation Ruihan Yang1*, Caiqi Zhang2*, Zhisong Zhang3†, Xinting Huang3, Dong Yu3,Nigel Collier2†,Deqing Yang1† 1Fudan University2University of Cambridge3Tencent AI Lab {rhyang17,deqingyang}@fudan.edu.cn, {cz391,nhc30}@cam.ac.uk, zhisonzhang@tencent.com Abstract Large Langua... | https://arxiv.org/abs/2505.16922v1 |
(Zhang et al., 2024a,b; Yang et al., 2024b). Current research on uncertainty expression in LLMs focuses primarily on short-form QA, where responses typically contain fewer than ten words (Kuhn et al., 2023; Lin et al., 2023; Fadeeva et al., 2023; Wang et al., 2024). However, real-world applications often require much l... | https://arxiv.org/abs/2505.16922v1 |
Models are more likely to use uncertainty expressions in short-form QA than in long-form QA (Section 5). Given that UNCLEprovides a direct compar- ison between short- and long-form uncertainty expressions, we investigate strategies to enhance model performance in both formats (Contribution #3; Section 6). We consider b... | https://arxiv.org/abs/2505.16922v1 |
remains chal- lenging due to the complexity of handling mixed uncertainties across multiple aspects in open-ended questions. Recent work has explored this challenge. LoGU (Yang et al., 2024b) proposes a two-step training framework: first, supervised fine-tuning to mitigate uncertainty suppression in long-form responses... | https://arxiv.org/abs/2505.16922v1 |
the most important and relevant properties for answering questions. For instance, birth date and birthplace are essential for biographies, while founders and 3 Correct Incorrect Uncertain Known Acor kn Aincor kn Aunc kn Akn Unknown Acor unk Aincor unk Aunc unk Aunk Acor Aincor Aunc Table 2: Uncertainty confusion matrix... | https://arxiv.org/abs/2505.16922v1 |
evaluation metrics to comprehensively assess the model’s ability to express uncertainty: Metric 1 (Factual Accuracy) LetAcordenote the set of correct aspects, and Aincor denote the set of incorrect aspects in the response. The Factual Accuracy (FA) is then defined as FA =|Acor| |Acor|+|Aincor|. FA measures the proporti... | https://arxiv.org/abs/2505.16922v1 |
proportion of aspects that are correctly expressed, i.e., the model maintains correct expres- sions for aspects it knows and expresses aspects it does not know as uncertainty. Evaluation Pipeline. Figure 2 illustrates the overview of our evaluation pipeline. Step 1: Known/Unknown Detection. To assess whether the model ... | https://arxiv.org/abs/2505.16922v1 |
all models are with UUR below 10%, indi- cating a limited ability to express unknown cases through uncertainty expressions. UA generally re- mains below 50%, and open-source models per- form generally better. A closer analysis reveals that open-source models tend to produce more un- certainty expressions , resulting in... | https://arxiv.org/abs/2505.16922v1 |
71.6 53.5 58.1 67.5 63.6 Pair-Few 54.2 46.8 2.77 79.7 47.7 60.0 45.4 16.0 83.6 55.6 Self-Refine 41.7 43.1 8.60 76.3 42.5 45.1 42.6 7.40 76.8 45.8TrainingShort-DPO 53.4 51.9 10.8 79.5 47.0 69.8 56.7 45.8 77.0 64.1 Mix-DPO 56.9 54.6 43.1 61.2 53.7 64.1 54.9 28.1 81.9 59.5 Long-DPO 53.3 59.6 37.8 62.2 52.0 70.1 51.6 58.1 ... | https://arxiv.org/abs/2505.16922v1 |
percentage of aspects expressed as cer- tain in both short- and long-form QA, while U-U 7 $6$6$6Unc-Zero0.17.591.80.6 Unc-Zero0.214.384.50.6Long-Form$6Short-DPO40.129.127.43.4 Short-DPO0.669.829.60$6Mix-DPO54.613.424.67.4 Mix-DPO20.738.333.47.6$6Long-DPO23.548.326.41.8 Long-DPO16.539.937.56.1LlamaMistralShort-FormFigur... | https://arxiv.org/abs/2505.16922v1 |
forms. Limitation Known and unknown detection To assess the model’s known and unknown knowledge, we em- ploy a multiple sampling method. Increasing the number of sampling iterations could enhance the accuracy of the knowledge estimation. Alternative approaches (Gekhman et al., 2024b; Yang et al., 2024c) may also be app... | https://arxiv.org/abs/2505.16922v1 |
In Pro- ceedings of the 2021 Conference on Empirical Meth- ods in Natural Language Processing , pages 6491– 6506, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingx- uan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu... | https://arxiv.org/abs/2505.16922v1 |
Linguistics. Zorik Gekhman, Gal Yona, Roee Aharoni, Matan Eyal, Amir Feder, Roi Reichart, and Jonathan Herzig. 2024a. Does fine-tuning LLMs on new knowledge encourage hallucinations? In Proceedings of the 2024 Conference on Empirical Methods in Natu- ral Language Processing , pages 7765–7784, Miami, Florida, USA. Assoc... | https://arxiv.org/abs/2505.16922v1 |
, pages 822–835. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd Inter- national Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings . Lorenz Kuhn, Yarin Gal, and Sebastian Farquhar. 2023. Semantic uncertainty: Ling... | https://arxiv.org/abs/2505.16922v1 |
Pang Koh, Mohit Iyyer, Luke Zettle- moyer, and Hannaneh Hajishirzi. 2023b. FActScore: Fine-grained atomic evaluation of factual precision in long form text generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages 12076–12100, Singa- pore. Association for Computationa... | https://arxiv.org/abs/2505.16922v1 |
Nigel Collier, Dong Yu, and De- qing Yang. 2024b. Logu: Long-form generation with uncertainty expressions. Yuqing Yang, Ethan Chern, Xipeng Qiu, Graham Neu- big, and Pengfei Liu. 2024c. Alignment for honesty. InAdvances in Neural Information Processing Sys- tems 38: Annual Conference on Neural Information Processing Sy... | https://arxiv.org/abs/2505.16922v1 |
Vendetta ", "prompt ": "In a paragraph , introduce the movie V for Vendetta , including duration in minutes , original language , production designer , producer , distribution format , award received .", "individual_qa ": [{"question ": " What is the duration of the movie V for Vendetta in minutes ?", "answer ": ["132"... | https://arxiv.org/abs/2505.16922v1 |
answer , this includes cases where the model answer is only partially consistent with the gold answer but does not introduce incorrect information . - NS: If the model answer is definitive but contradicts the gold answer . Output Format : Your responses must follow the format demonstrated in the examples below : ### Qu... | https://arxiv.org/abs/2505.16922v1 |
knowledge . - S: If the statement in the paragraph about this question is definitive and does not contradict the gold answer , this includes cases where the model answer is only partially consistent with the gold answer but does not introduce incorrect information . - NS: If the statement in the paragraph about this qu... | https://arxiv.org/abs/2505.16922v1 |
use Llama-3-8B- Instruct (Meta, 2024) and Mistral-7B- Instruct (Jiang et al., 2023) as base models. Training Data We construct three types of train- ing data: Idk-Dataset, which helps the model learn to express uncertainty for short questions; LoGU-Dataset, which is used for long-form uncertainty expression; and Mix-Da... | https://arxiv.org/abs/2505.16922v1 |
fair- ness, we use the same amount of training data for all three methods in both the SFT and DPO stages (i.e., 40k for the SFT stage and 20k for the DPO stage). Fine-tuning Details We run SFT and DPO ex- periments with 8 NVIDIA GPUs. We conduct experiments with the LlamaFactory code base3. Building upon prior research... | https://arxiv.org/abs/2505.16922v1 |
arXiv:2505.16927v1 [cs.CL] 22 May 2025Latent Principle Discovery for Language Model Self-Improvement Keshav Ramji∗, Tahira Naseem, Ramón Fernandez Astudillo IBM Research AI Abstract When language model (LM) users aim to improve the quality of its generations, it is crucial to specify concrete behavioral attributes that... | https://arxiv.org/abs/2505.16927v1 |
interpretable constitutions Ctand models trained to follow them Mt. (Right) The STaPLe algorithm induces self-improvement in AlpacaEval win-rate over three iterations for all three language models. generation tasks that are challenging to verify; identifying situations for a human to intervene and induce a refined resp... | https://arxiv.org/abs/2505.16927v1 |
to design an instructable, principle- following reward model (RM). ConstitutionalExperts (Petridis et al., 2024) and SPRI (Zhan et al., 2025) address the problem of mapping prompts to principles. Deliberative Alignment (Guan et al., 2025) introduces CoT reasoning over safety specifications, and trains models to learn t... | https://arxiv.org/abs/2505.16927v1 |
multi-turn RL formulation that boosts the quality of the initial attempt and leverages reward shaping to incentivize self-correction to improve the refined response. Beyond individual output corrections, recent work has shown that models can bootstrap their underlying capabilities in an iterative fashion over time. Sev... | https://arxiv.org/abs/2505.16927v1 |
match metric used for verifiable responses can be seen as one such instantiation. Given a dataset D={(xi, y1 i, yG i)}n i=1, where yG iis the gold response and y1 iis model’s initial response for the ithsample, we aim to learn a latent response-improvement reasoning trace zisuch that the probability of producing a resp... | https://arxiv.org/abs/2505.16927v1 |
we use a sparse approximation of this distribution, that assigns zero probability unless there is an improvement in similarity function f: p(yG|x, y1, z, y2)∝f(y2, yG)−f(y1, yG),iff(y2, yG)> f(y1, yG) 0, otherwise We sample from ˜p(y2, z|x, y1, yG;θ)via rejection sampling. Given a sample yn∼˜p(y2, z| x, y1;θ), we acce... | https://arxiv.org/abs/2505.16927v1 |
like projected gradient descent could be used to solve for the Lagrange multipliers, this is expensive for deep neural networks, and as such, is impractical in our case. Instead, we suggest that performing clustering methods on a set of posterior samples and retaining only the representative elements fulfills an equiva... | https://arxiv.org/abs/2505.16927v1 |
both the single-iteration and multi-iteration settings, in addition to the scores of each model’s initial policy. 1.Prompted self-refinement to directly produce a self-critique and revision, akin to Self-Refine, without any principle or specific feedback criterion provided a priori. 2. Supervised fine-tuning on the gol... | https://arxiv.org/abs/2505.16927v1 |
outpaces the STaR baseline by a sizable margin throughout the execution of both algorithms. We include the full set of results in Appendix G. By iteration 3, the STaPLe scores outperform STaR and the initial policy on average across the three models by +0.16and+0.29on MT-Bench (avg.); +3.6% and +9.2% on AlpacaEval win-... | https://arxiv.org/abs/2505.16927v1 |
model converges to learning a relatively stable distribution of principles. In particular, the size of the constitution by iteration 4 is roughly 50% of the iteration 1 size, or even smaller. This finding is reinforced by an analysis of the principle discovery rate – the fraction of refinement samples with new, unseen ... | https://arxiv.org/abs/2505.16927v1 |
self-improvement method which uses model-generated latent principles to learn intrinsic self-correction. These serve a purpose akin to a reasoning chain-of- thought, boosting the quality of LM generations on alignment-focused benchmarks. Furthermore, our approximate posterior-regularized Monte Carlo EM algorithm shows ... | https://arxiv.org/abs/2505.16927v1 |
editors, Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages 1423–1433, Mexico City, Mexico, June 2024b. Association for Computational Linguistics. doi: 10.18653/v1/2024. naacl-long.78. URL https:/... | https://arxiv.org/abs/2505.16927v1 |
Ma, Y . Liu, Y . Guo, Y . Wu, Y . Ou, Y . Zhu, Y . Wang, Y . Gong, Y . Zou, Y . He, Y . Zha, Y . Xiong, Y . Ma, Y . Yan, Y . Luo, Y . You, Y . Liu, Y . Zhou, Z. F. Wu, Z. Z. Ren, Z. Ren, Z. Sha, Z. Fu, Z. Xu, Z. Huang, Z. Zhang, Z. Xie, Z. Zhang, Z. Hao, Z. Gou, Z. Ma, Z. Yan, Z. Shao, Z. Xu, Z. Wu, Z. Zhang, Z. Li, Z.... | https://arxiv.org/abs/2505.16927v1 |
Fadnis, C. Gunasekara, Y .-S. Lee, L. Popa, V . Shah, H. Zhu, D. Contractor, and M. Danilevsky. Mtrag: A multi-turn conversational benchmark for evaluating retrieval- augmented generation systems, 2025. URL https://arxiv.org/abs/2501.03468 . S. Kim, J. Suk, S. Longpre, B. Y . Lin, J. Shin, S. Welleck, G. Neubig, M. Lee... | https://arxiv.org/abs/2505.16927v1 |
Srikumar, editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) , pages 574–582, Bangkok, Thailand, Aug. 2024. Association for Computational Linguistics. doi: 10.18653/v1/2024.acl-short.52. URL https://aclanthology.org/2024.acl-short.52/ . 12 D. Phan, ... | https://arxiv.org/abs/2505.16927v1 |
Yang, P. Qi, S. Zhang, Y . Bengio, W. Cohen, R. Salakhutdinov, and C. D. Manning. Hot- potQA: A dataset for diverse, explainable multi-hop question answering. In E. Riloff, D. Chi- ang, J. Hockenmaier, and J. Tsujii, editors, Proceedings of the 2018 Conference on Empir- ical Methods in Natural Language Processing , pag... | https://arxiv.org/abs/2505.16927v1 |
. . . . . . 30 L.2 Critique Generation Prompt . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 L.3 Principle-Conditioned Refinement Prompt . . . . . . . . . . . . . . . . . . . . 30 M Ablations 31 M.1 Label Replacement Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 M.2 LLM-as-a-Judge Reject... | https://arxiv.org/abs/2505.16927v1 |
include the hyperparameters used and model training details in Appendix C and the prompts used in the STaPLe algorithm in Appendix L. We make all evaluation results available in tabular format throughout the main paper and the appendices for comparability. We also will publicly release the code for the STaPLe algorithm... | https://arxiv.org/abs/2505.16927v1 |
Rejection Sampling Rule Recall the intractable posterior which we obtain from the MC-EM gradient: p(y2, z|x, y1, yG) =p(yG|x, y1, z, y 2)·p(y2, z|x, y1;θ) p(yG|x, y1) This can be approximated via Monte Carlo Expectation-Maximization (Wei and Tanner, 1990), where sampling techniques are used to obtain samples from the i... | https://arxiv.org/abs/2505.16927v1 |
an input x, an initial model response y1∼πθ(· |x), a latent principle z∼πθ(· |x, y1, yG)and critique of y1with respect to zdenoted by c, and a refinement y2∼πθ(· |x, y1, z, c). Then, the EM gradient given by Equation 1 is equivalent to the REINFORCE score-function gradient under variance-reduced self-play, given by Equ... | https://arxiv.org/abs/2505.16927v1 |
of both algorithms, even in spite of the improvements of Llama-8B and Granite-8B saturating by the end of iteration 3. While both algorithms have fairly similar MT-Bench Turn-1 scores by iteration 4, the Turn-2 score is substantially higher (average of +0.22) for STaPLe. We observe similar general trends for the models... | https://arxiv.org/abs/2505.16927v1 |
self-correction, but without the principle, so we use the principle invoked by the STaPLe model in the Prometheus judge rubric. Table 3: Analysis of the Prometheus-8x7B-v2.0 model’s judgements on the self-correction responses of the STaPLe model against the STaR baseline. The baseline win-rate against the base policy i... | https://arxiv.org/abs/2505.16927v1 |
previous iteration’s policy. Model IFEval Prometheus Win-rate Llama-3.1-8B-Instruct STaPLe Iter 1 (28.2k) 65.6% STaPLe Iter 2 (6.1k) 58.2% STaPLe Iter 3 (6.3k) 54.3% STaPLe Iter 4 (6.6k) 49.4% Granite-3.1-8B-Instruct STaPLe Iter 1 (24.1k) 65.1% STaPLe Iter 2 (5.2k) 62.3% STaPLe Iter 3 (5.9k) 58.0% STaPLe Iter 4 (6.3k) ... | https://arxiv.org/abs/2505.16927v1 |
corpus on which at least one principle-conditioned refinement attempt improved over the initial response. We compare the refinement rates between the unconstrained and constrained versions of STaPLe in Figures 5 and J. We observe a similar trend, where Qwen-7B starts with th highest rate (above 0.61) and remains the hi... | https://arxiv.org/abs/2505.16927v1 |
Avoiding Harm and Sensitivity 8. Specificity and Completeness 9. Avoiding Assumptions 10. Challenge Assumptions 11. Be More Direct and Clear in Addressing Concerns 12. Acknowledge and Address Previous Misconceptions Clearly 13. Simplicity and Gradual Complexity 14. Be more assertive in responses to known information 15... | https://arxiv.org/abs/2505.16927v1 |
and Specificity in Medical Conditions 41. Personalization and Specificity 42. Character Development and Consistency 43. Clarity and Accuracy in Historical Context 44. Clarity and Organization Through Structure 45. Clarity and Specificity in Categorization 46. Verify Information Accurately Before Providing 47. Clarity a... | https://arxiv.org/abs/2505.16927v1 |
outline in Section 3.1, we explore using the mode of each clustering based on the counts of principles invoked and an augmentation on the medoid scheme, where we only perform the label replacement if the difference in perplexity of the trajectory is bounded by a threshold τPPL, which we take as 0.2. ˜Zmedoid ={mk:mk= a... | https://arxiv.org/abs/2505.16927v1 |
expend the inference-time compute to do so. We explore this setup using the Phi-4 model (Abdin et al., 2024), a 14B parameter model which reduces latency in performing N+ 1judge queries (one per refined response, along with the initial response), compared to a larger model such as Mixtral-8x22B or Llama-3.1-405B-Instru... | https://arxiv.org/abs/2505.16927v1 |
Medoids Iter 3 (6.9k) 7.17 7.54 6.80 39.8 70.4% Modes Iter 3 (6.9k) 7.12 7.54 6.70 39.2 68.8% PPL Iter 3 (6.8k) 7.15 7.53 6.78 39.6 69.7% Unconstrained Iter 4 (7.1k) 7.24 7.64 6.85 40.2 73.4% Medoids Iter 4 (7.2k) 7.22 7.60 6.84 39.9 72.1% Modes Iter 4 (7.1k) 7.14 7.56 6.73 39.1 69.7% PPL Iter 4 (7.1k) 7.17 7.55 6.79 4... | https://arxiv.org/abs/2505.16927v1 |
a Phi-4 model as a judge to score similarity to the gold response for rejection sampling. We include Constrained STaPLe with Rouge-L, to make a direct comparison, denoted "STaPLe w/ Rouge". Model MT-Bench (avg) MT-Bench (T1) MT-Bench (T2) AlpacaEval IFEval WR Llama-3.1-8B-Instruct Initial Policy 7.46 8.09 6.83 26.9 – S... | https://arxiv.org/abs/2505.16927v1 |
two terms over a clustering assignment: 1. the inter-medoid diversity and 2. the intra-cluster tightness. The former is denoted by the average cosine-similarity (abbreviated as "cossim" henceforth) between each pair of medoids, while the latter is average cosine similarity of the points in their cluster to their own me... | https://arxiv.org/abs/2505.16927v1 |
of clusters decreases, a more permissive threshold suffices to balance diversity and cluster tightness. We find that the optimized thresholds result in very similar results, albeit with slight improvements across both MT-Bench turns, and thus the average score as well. M.3.1 Diversity of Constitutions with Manually Sel... | https://arxiv.org/abs/2505.16927v1 |
delight. The attention to detail and the emphasis on seasonal ingredients were evident in every dish. 36 Our trip to Japan was more than just a vacation; it was a cultural immersion. The country’s blend of tradition and modernity, its respect for nature, and its culinary artistry left an indelible mark on us. Japan, wi... | https://arxiv.org/abs/2505.16927v1 |
apply, regardless of previous academic experience. This inclusivity aligns with your request for a college with open enrollment. 37 The university’s regional accreditation by the HLC ensures that its degrees are recognized and respected by employers, academic institutions, and professional organizations. This accredita... | https://arxiv.org/abs/2505.16927v1 |
its commitment to [Company Value/Mission], which resonates with my professional aspirations. I am eager to bring my unique blend of skills and experience to [Company Name] and contribute to your team’s success. I am available for an interview at your earliest convenience and can be reached at 631-481-4867. Thank you fo... | https://arxiv.org/abs/2505.16927v1 |
tone. 39 Despite seeming to reflect a slight "upward bias", using keywords like "meticulous examination" and "maintains its resolute stance, " it balances this with phrases such as "critical significance", "incumbent upon us", which retain seriousness and a balanced outlook, as desired. N.2.2 Principle: Tone and Commun... | https://arxiv.org/abs/2505.16927v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.