text string | source string |
|---|---|
sampled token t1as an one-hot vector t1∈ {0,1}|V|withP ktk 1= 1, its expectation under the multinomial distribution is the first concept token : ct1=E[t1] =X t1p(t1|x)t1=p(· |x)∈∆|V|−1, (9) which aligns the concept token in Definition 1. By a linear approximation of p(y|x,·)around the mean, we obtain p(y|x) =X t1p(t1|x... | https://arxiv.org/abs/2505.15778v1 |
Soft Thinking can be plugged into the CoT pipeline of any LLM with minimal engineering effort. We implement our Soft Thinking on SGLang [ 39], enabling fast inference (see Appendix A.3 for implementation details). We evaluate our method on a server equipped with eight NVIDIA H100 80GB GPUs. 6 Accuracy ↑ Generation Leng... | https://arxiv.org/abs/2505.15778v1 |
Soft Thinking and other baseline methods on mathematical and coding datasets in Table 1 and Table 2, respectively. Improved Pass@1 Accuracy. Our proposed Soft Thinking consistently enhances Pass@1 accu- racy across all evaluated math and coding benchmarks, demonstrating its broad effectiveness and generalization abilit... | https://arxiv.org/abs/2505.15778v1 |
correct solution, directly translating to reduced token usage. Results also stand in stark contrast to the greedy decoding baseline, which, while also reducing token usage, suffers from substantial drops in accuracy, particularly on complex code generation tasks where the loss of diversity in reasoning paths leads to p... | https://arxiv.org/abs/2505.15778v1 |
1.00 I 1.00'll 1.00 add 1.00 these 0.65 two 1.00 products 0.91 together 1.00: 0.87' ' 1.001 1.007 0.95 2 0.40 the 0.35 results 0.09 to 0.13, 0.05 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 972 1.00 plus 1.00' ' 1.001 1.00, 1.002 1.009 1.000 1.00 equals 1.00' ' 1.001 1.00, 1.004 1.006 1.002 1.00.\n 0.50</think> 1.0... | https://arxiv.org/abs/2505.15778v1 |
repeat until it hits the maximum generation length. This OOD-induced collapse significantly increases the average generation length across all problems. However, for problems that are solved correctly (typically those requiring shorter reasoning chains), the average length remains relatively low, as these cases are les... | https://arxiv.org/abs/2505.15778v1 |
2016. [7]AA Ivanova, Z Mineroff, V Zimmerer, N Kanwisher, R Varley, and E Fedorenko. The language network is recruited but not required for non-verbal semantic processing. biorxiv, 696484, 2019. 10 [8]Yael Benn, Anna A Ivanova, Oliver Clark, Zachary Mineroff, Chloe Seikus, Jack Santos Silva, Rosemary Varley, and Evelin... | https://arxiv.org/abs/2505.15778v1 |
preprint arXiv:2406.12775 , 2024. [23] Yuval Shalev, Amir Feder, and Ariel Goldstein. Distributional reasoning in llms: Parallel reasoning processes in multi-hop reasoning. arXiv preprint arXiv:2406.13858 , 2024. [24] Xinyi Wang, Lucas Caccia, Oleksiy Ostapenko, Xingdi Yuan, William Yang Wang, and Alessandro Sordoni. G... | https://arxiv.org/abs/2505.15778v1 |
language models. arXiv preprint arXiv:2108.07732 , 2021. [37] Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Ar- mando Solar-Lezama, Koushik Sen, and Ion Stoica. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv:2403.0797... | https://arxiv.org/abs/2505.15778v1 |
tasks. A.3 Implementation of Soft Thinking on SGLang In this appendix, we describe the engineering modifications made to the SGLang inference engine (v0.4.6.post1 ) to support our proposed Soft Thinking method. We highlight the core code changes, affected files, and provide high-level code snippets to clarify the new r... | https://arxiv.org/abs/2505.15778v1 |
topk_probs , forward_batch . topk_indices ) 7elif input_embeds is None : 8 hidden_states = self . embed_tokens ( input_ids ) 5.schedule_batch.py ,scheduler.py ,scheduler_output_processor_mixin.py •Purpose : State management and output tracking for soft thinking. •Key changes : 1# Pseudocode for Cold Stop 2if entropy < ... | https://arxiv.org/abs/2505.15778v1 |
arXiv:2505.15781v1 [cs.CL] 21 May 2025dKV-Cache: The Cache for Diffusion Language Models Xinyin Ma Runpeng Yu Gongfan Fang Xinchao Wang∗ National University of Singapore maxinyin@u.nus.edu, xinchao@nus.edu.sg Abstract Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language ... | https://arxiv.org/abs/2505.15781v1 |
the challenge of integrating the KV-Cache mechanism into diffusion language models and operate without autoregressive or semi-autoregressive structures [ 2]. We identify two core reasons that prevent the direct usage of KV-Cache in DLMs. (1) KV-Cache hinges on the assumption that the key and value states of previously ... | https://arxiv.org/abs/2505.15781v1 |
attention. (2) We propose two practical variants of our method: dKV- Cache-Decode, which enables long-term cache reuse, and dKV-Cache-Greedy, which reduces the per-step time complexity for faster decoding. (3) Extensive experiments on DLMs demonstrate that our approach achieves 2–10 ×inference speedup with minimal or n... | https://arxiv.org/abs/2505.15781v1 |
distribution pdata(x0). Each token is represented by a one-hot vector with Vcategories, where Vis the vocabulary size. The forward process adds noise in the original sequence x0, which, in the discrete diffusion models here, takes the form of masking some of the tokens randomly. The masking process can be controlled by... | https://arxiv.org/abs/2505.15781v1 |
the targeted computation only for the current decoding token. We conclude that standard KV-Cache is fundamentally incompatible with diffusion language models for two reasons: •Timestep-variant key and value states. In the autoregressive setting, every time step shares a single, causally growing set of key and value ten... | https://arxiv.org/abs/2505.15781v1 |
the early stages of the denoising process. This is reflected by prominent changes along the diagonal in Figure 2(c), corresponding to the i-th decoding step which decodes the i-th token. These observations provide key insights into the temporal structure of discrete diffusion models and motivate the design of our KV-Ca... | https://arxiv.org/abs/2505.15781v1 |
introduce one-step delayed caching. At timestep t, we use the masking state from the previous step, Mt−1, to determine which tokens are cacheable. The method, named dKV-Cache-Decode, is finally formalized as: zt= softmax QMt−1 t KI t⊤ √dk! VI twith KI t= concat _reorder KI\M t−1 t−1,KMt−1 t VI t= concat _reorde... | https://arxiv.org/abs/2505.15781v1 |
assess 6 Table 1: Benchmark results on LLaDA-8B-Instruct. We use zero-shot evaluation here. Detailed configuration is listed in the Appendix. We set the cache refresh step for dKV-Cache-Decode to be 8 and dKV-Cache-Greedy to be 2. The window size of dKV-Cache-Greedy is listed in the bracket. Base Few-Steps dKV-Cache-Gr... | https://arxiv.org/abs/2505.15781v1 |
/|Ti|, where Tis the total number of decoding steps. Tidenotes the number of tokens processed at step i(normally the whole sequence) and Tcache i is the subset of tokens whose KV pairs are reused from cache at timestep i, which is |Mi|. 4.2 Performance and Speed with dKV-Cache We begin by addressing the central questio... | https://arxiv.org/abs/2505.15781v1 |
illustrates the impact of applying a one-step delay to the cache mechanism. Without the delay, performance remains acceptable at low cache ratios but degrades rapidly as the cache ratio increases, ultimately collapsing to near-zero accuracy. In contrast, introducing a one-step delay stabilizes the generation quality, e... | https://arxiv.org/abs/2505.15781v1 |
may degrade performance. However, under the same refresh interval, dKV-Cache-Greedy consistently achieves higher speedups than dKV-Cache-Decode, highlighting its potential advantage when refresh frequency is relaxed. 5 Conclusions and Limitations In this work, we explore the feasibility of incorporating the caching mec... | https://arxiv.org/abs/2505.15781v1 |
Shantanu Jain, William Saunders, Christopher Hesse, Andrew N. Carr, Jan Leike, Josh Achiam, Vedant Misra, Evan Morikawa, Alec Radford, Matthew Knight, Miles Brundage, Mira Murati, Katie Mayer, Peter Welinder, Bob McGrew, Dario Amodei, Sam McCandlish, Ilya Sutskever, and Wojciech Zaremba. Evaluating large language model... | https://arxiv.org/abs/2505.15781v1 |
processing systems , 33:6840–6851, 2020. [25] Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini, Patrick Forré, and Max Welling. Argmax flows and multinomial diffusion: Learning categorical distributions. Advances in neural information processing systems , 34:12454–12465, 2021. [26] Coleman Hooper, Sehoon Kim, Hiva Mohamm... | https://arxiv.org/abs/2505.15781v1 |
estimating gradients of the data distribution. Advances in neural information processing systems , 32, 2019. [42] Jianlin Su, Murtadha Ahmed, Yu Lu, Shengfeng Pan, Wen Bo, and Yunfeng Liu. Roformer: Enhanced transformer with rotary position embedding. Neurocomputing , 568:127063, 2024. [43] Qwen Team. Qwen2.5 technical... | https://arxiv.org/abs/2505.15781v1 |
that are less efficient than the simple concatenation in contiguous space used in ARs. In dKV-Cache, the cache process involves two additional indexing operations: (1) At the cache step: After computing keys and values, we need to gather the corresponding states of cached tokens at non-continuous positions. (2) At the ... | https://arxiv.org/abs/2505.15781v1 |
matrices, which, to cache which tokens, can only be known after the decoding results at step t. We present the pseudo-algorithm of our approach in Algorithm 1. While it largely improves inference speed over the naive implementation, the concat and reorder operations still introduce some overhead. We believe there is su... | https://arxiv.org/abs/2505.15781v1 |
for Dream-Base-7B. Un-Shift Right-Shift Un&Right Shift MMLU 71.78 64.60 71.73 GSM8K 76.34 32.68 77.71 C Evaluation Details C.1 For LLaDA We re-implemented the evaluation of LLaDA on those reported datasets. We generate and extract the final answer instead of comparing the log prob in the multiple-choice question. Thus,... | https://arxiv.org/abs/2505.15781v1 |
distance: \boxed{72} km dKV-Cache- Decode, Refresh = 41. Calculate the distance Lily runs in the first 4 hours: - Distance = Speed × Time = 12 km/h × 4 h = 48 km 2. Calculate the distance Lily runs in the next 4 hours: - Distance = Speed × Time = 6 km/h × 4 h = 24 km 3. Add the distances from both periods to find the t... | https://arxiv.org/abs/2505.15781v1 |
could enjoy the scenery and the fresh air. After a while, Joey’s parents started to see Rachel in a different light. They realized that she was a good person and that she loved Joey very much. They decided to give their blessing to the marriage. Finally, Joey and Rachel got married and lived happily ever after. dKV-Cac... | https://arxiv.org/abs/2505.15781v1 |
(Entropy)In the first 4 hours, Lily runs 12 kilometers per hour, so she runs a total of 12 * 4 = 48 kilometers. In the next 4 hours, Lily runs 6 kilometers per hour, so she runs a total of 6 * 4 = 24 kilometers. Therefore, in 8 hours, Lily can run a total of 48 + 24 = 72 kilometers. #### 72 dKV-Cache- Decode, Refresh =... | https://arxiv.org/abs/2505.15781v1 |
arXiv:2505.15784v1 [cs.LG] 21 May 2025Large Language Models as Computable Approximations to Solomonoff Induction Jun Wan UBS AG jun.wan@ubs.comLingrui Mei State Key Lab of AI Safety meilingrui25b@ict.ac.cn Abstract The rapid advancement of large language models (LLMs) calls for a rigorous theo- retical framework to exp... | https://arxiv.org/abs/2505.15784v1 |
framework for universal induction. Our primary contribution is a construc- tive mathematical proof establishing that the standard LLM training paradigm—specifically, the minimization of prediction loss—serves as a computational approximation to the Solomonoff prior. This is achieved by reinterpreting the optimization p... | https://arxiv.org/abs/2505.15784v1 |
both specific Turing machines, denoted T, and universal Turing machines (UTMs), denoted U. A UTM Ucan simulate any other TM by processing a program pand its input was arguments, denoted U(p, w). From a theoretical perspective, large language models (LLMs) can be viewed as specific Turing machines. Given an input contex... | https://arxiv.org/abs/2505.15784v1 |
summation encompasses all programs psuch thatU(p)outputs a string beginning with x. This formulation embodies Occam’s razor, as shorter programs contribute more significantly to M(x). Two critical design choices warrant explanation: (1) The inclusion of outputs beginning with xfacilitates prediction—having observed seq... | https://arxiv.org/abs/2505.15784v1 |
the decoded xwith the generated continuation, the final output is the complete sequence x∗. This con- struction f(x, s)has the following two key properties: (1) For a fixed input x, the number of decoding iterations n(x)is deterministic; the random seed scan be any natural number. (2) Since the model parameters m(2)rem... | https://arxiv.org/abs/2505.15784v1 |
key approximation: M(xt+1|x1:t)≈t2 4(t+ 1)2P(xt+1|x1:t) (18) It should be noted that M(x)is a semi-measure and needs to be normalized when converting to a probability. Sincet2 4(t+1)2is a value independent of the token, it will automatically cancel out during normalization. This result indicates that the prediction pro... | https://arxiv.org/abs/2505.15784v1 |
which there exist multiple computable distribu- tions µ1, µ2,···,that can serve as valid solu- tions, with their prefix Kolmogorov complexi- tiesK(µ)being approximately equal. Suppose we have collected a large number of sample se- quences x1:t, where different subsets may orig- inate from different computable distribut... | https://arxiv.org/abs/2505.15784v1 |
article classification dataset [Zhang et al., 2015]. For the datasets provided by Saravia et al. [2018] and Zhang et al. [2015], which already contain predefined training and test splits, we randomly sampled a subset from the original training set as our selection pool while using the official test set for evaluation. ... | https://arxiv.org/abs/2505.15784v1 |
as computable approximations of Solomonoff induction paves the way for more principled advancements in their design and application, encouraging a perspective that recognizes them as sophisticated, albeit approximate, universal inductive reasoners. 9 References Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, I... | https://arxiv.org/abs/2505.15784v1 |
17(3):840–865, 1989. 10 DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Ch... | https://arxiv.org/abs/2505.15784v1 |
Frank Zhang, Gabriel Synnaeve, Gabrielle Lee, Georgia Lewis Anderson, Govind Thattai, Graeme Nail, and et al. The llama 3 herd of models, 2024. URL https://arxiv.org/abs/2407.21783 . Jordi Grau-Moya, Tim Genewein, Marcus Hutter, Laurent Orseau, Grégoire Delétang, Elliot Catt, Anian Ruoss, Li Kevin Wenliang, Christopher... | https://arxiv.org/abs/2505.15784v1 |
Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, and Xueqi Chen. Slang: New concept comprehension of large language models. arXiv preprint arXiv:2401.12585 , 2024a. Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Jiayi Mao, and Xueqi Cheng. " not aligned" is not" malicious": Being careful about hallucinations of l... | https://arxiv.org/abs/2505.15784v1 |
Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, Chuning Tang, Congcong Wang, Dehao Zhang, Enming Yuan, Enzhe Lu, Fengxiang Tang, Flood Sung, and et al. Kimi k1.5: Scaling reinforcement learning with llms, 2025. URL https://arxiv.org/abs/2501.12599 . 13 Qwen Team. Qwq: Reflect deeply on the boundaries ... | https://arxiv.org/abs/2505.15784v1 |
gpt4-style language model with multimodal inputs? In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages 7930–7957, 2024b. Jiaxin Zhang, Zhongzhi Li, Mingliang Zhang, Fei Yin, Chenglin Liu, and Yas... | https://arxiv.org/abs/2505.15784v1 |
of UTM Uwith program pand input w. •U(p): Output of UTM Ugiven program p. •x1:t: An input sequence of tokens (context) of length t. •xi: The i-th token in a sequence. •x∗: A sequence starting with prefix x. In LLM generation (Def 1), x∗=x◦r, the full sequence generated from prompt xand model output r. •V: V ocabulary o... | https://arxiv.org/abs/2505.15784v1 |
of the generation process, thereby eliminating randomness typically introduced by temperature-based sampling. This determinism is methodologically important for several reasons: 1.Reproducibility: It ensures that results are perfectly reproducible given the same model and input. 2.Alignment with Theoretical Framework: ... | https://arxiv.org/abs/2505.15784v1 |
arXiv:2505.15792v1 [cs.CL] 21 May 2025Long-Form Information Alignment Evaluation Beyond Atomic Facts Danna Zheng1, Mirella Lapata1, Jeff Z. Pan1,2 1School of Informatics, University of Edinburgh, UK 2Huawei Edinburgh Research Centre, CSI, UK dzheng@ed.ac.uk, mlap@inf.ed.ac.uk, http://knowledge-representation.org/j.z.pa... | https://arxiv.org/abs/2505.15792v1 |
errors, this approach has a critical blind spot: it overlooks re- lationships and dependencies between facts. Even when all individual statements are accurate, re- ordering them can reverse implied causal chains and mislead readers. As illustrated in Figure 1, the Lie version suggests that Amy’s outing with John trigge... | https://arxiv.org/abs/2505.15792v1 |
where higher yindicates stronger alignment of b with respect to a. 2.2 Benchmarks Early benchmarks mainly addressed sentence- level alignment, such as FEVER (Thorne et al., 2018), FEVEROUS (Aly et al., 2021), and A VERITEC (Schlichtkrull et al., 2023). More recent efforts target longer texts and diverse do- mains. Summ... | https://arxiv.org/abs/2505.15792v1 |
randomly sample pairs (s, g) from each, where sis the source document and g is its corresponding summary, which we label as correct target text. •SummScreen (Chen et al., 2022): TV-series transcripts paired with human-written recaps capturing dialogue-driven narratives and char- acter actions. •BookSum (Kryscinski et a... | https://arxiv.org/abs/2505.15792v1 |
each step, LLM is explicitly instructed that the new event occurs after the existing text and should be integrated as the next logical event in the narrative. The LLM is asked to continue the paragraph in a natural and coherent manner, without inserting un- necessary transitional phrases or restructuring ear- lier cont... | https://arxiv.org/abs/2505.15792v1 |
ator using the AUC-ROC score, which quantifies the evaluator’s ability to distinguish the correct tar- get texts from deceptive alternatives (“lies”) across varying levels of difficulty. For each target text, the evaluator assigns a score indicating how wellit aligns with the given source. To compute the AUC-ROC for a ... | https://arxiv.org/abs/2505.15792v1 |
AUC-ROC of only 64.23%, reflecting the inherent difficulty of the task and underscoring the pressing need for more effective information alignment evaluators. Fine-Grained Evaluators Suffers from Inher- ent Difficulty Fine-grained evaluation methods struggle to detect montage-style lies, as they often overlook the rela... | https://arxiv.org/abs/2505.15792v1 |
target texts are highly similar. This suggests that current models are not easily misled by paraphrasing, a desirable property in factuality evaluation. 5 D OVESCORE : A Fine-Grained Information Alignment Evaluation Framework As discussed in Section 4, current fine-grained evaluation methods are insufficiently equipped... | https://arxiv.org/abs/2505.15792v1 |
improves perfor- mance by 14.8%. The distribution of its sub-scores(SE,SEO,SD) in Figure 10 (Appendix C) high- lights the contribution of SEOin enhancing the model’s ability to distinguish between truthful and deceptive texts. Further evidence from Figure 4 reveals system- atic differences in how evaluators handle com-... | https://arxiv.org/abs/2505.15792v1 |
ensure the quality of the generated data, we conducted a man- ual evaluation with two human annotators: one isone of the authors of this paper, and the other is an external contributor who received compensation at the standard hourly rate designated for tutors and demonstrators at our university. References Rami Aly, Z... | https://arxiv.org/abs/2505.15792v1 |
Robust safety classifier against jailbreaking attacks: Adversarial prompt shield. In Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024) , pages 159–170, Mexico City, Mexico. Asso- ciation for Computational Linguistics. Donald E Knuth. 1998. The Art of Computer Program- ming: Sorting and Searching, vo... | https://arxiv.org/abs/2505.15792v1 |
for automatic evalu- ation of machine translation. In Proceedings of the 10 40th Annual Meeting of the Association for Compu- tational Linguistics , pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics. Nirmal Roy, Leonardo F. R. Ribeiro, Rexhina Blloshmi, and Kevin Small. 2024. Lea... | https://arxiv.org/abs/2505.15792v1 |
Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) , pag... | https://arxiv.org/abs/2505.15792v1 |
8 and 9. The subscore distribution of DoveScore is provided in Figure 10. 12 Algorithm 1: RANDOM SHUFFLE WITHINVERSIONS Input : A= (a1, a2, . . . , a m): original list of length m K: target inversion count, 0≤K≤m(m−1) 2 Output : B: a random permutation of AwithInv(B) =K /* Step 1: Initialize maximum inversion sequence ... | https://arxiv.org/abs/2505.15792v1 |
it as needed. Evaluation Criteria: Consistency (1-5) - the information alignment between the target text and the source text. A consistent target text contains only statements that are entailed by the source source text. Annotators were also asked to penalize target texts that contained hallucinated facts. 1 - worst, 5... | https://arxiv.org/abs/2505.15792v1 |
right after checking her email. Events: - Sarah checked her email - Sarah went out for lunch - Sarah called her friend - Sarah replied to a message Ordered Events : [Sarah checked her email, Sarah replied to a message, Sarah went out for lunch, Sarah called her friend] Now sort the following events based on the paragra... | https://arxiv.org/abs/2505.15792v1 |
arXiv:2505.15795v1 [cs.CL] 21 May 2025Reverse Engineering Human Preferences with Reinforcement Learning Lisa Alazraki∗ Imperial College LondonTan Yi-Chern CohereJon Ander Campos Cohere Maximilian Mozes CohereMarek Rei Imperial College LondonMax Bartolo Cohere Abstract The capabilities of Large Language Models (LLMs) ar... | https://arxiv.org/abs/2505.15795v1 |
optimise upstream preambles in an RL fashion asReinforcement Learning for Reverse Engineering (RLRE). There are several advantages to tuning an upstream preamble generator as opposed to directly overfitting the candidate-LLM to the judge-LLM’s rewards: (1) the specialised preamble generator can be smaller in size, henc... | https://arxiv.org/abs/2505.15795v1 |
by crafting adversarial attacks aimed at maximising the scores assigned by a judge-LLM to candidate responses. 2In this context, preambles are also known as system prompts. 2 Give gene ral advice to help answer the following question…: [q] Preamble generator p p’q + + R(q, c’ ) p +q Candidate-LLM Judge-LLM Training dat... | https://arxiv.org/abs/2505.15795v1 |
Similarly to [ 28], they append the tuned sequence to a pre-generated LLM response. Finally, [ 37] experiment with replacing responses with fixed instructions that invalidate the original LLM-as-a-judge prompt. Note that [ 28], [30] and [ 37] all observe that their attack can in large part be detected by measuring the ... | https://arxiv.org/abs/2505.15795v1 |
that all pipelines are trained with the same judge-LLM, i.e. Command R+ prompted as in [ 36]. We tune the Command R7B preamble generators on a Google Cloud TPU v5e containing 64 chips. We train the Llama 3.1 8B Instruct preamble generator on a single Nvidia H100 GPU. Candidate- and judge-LLMs from the Command family ar... | https://arxiv.org/abs/2505.15795v1 |
vulnerabilities in the LLM-as-a-judge framework to artificially boost their evaluation scores. We describe these additional baselines below. Note that all of them modify responses pre-generated using the non-attacked model. Verbosity bias attack. We ask the candidate-LLM to increase the length of a pre-generated respon... | https://arxiv.org/abs/2505.15795v1 |
8 8 8 9 9 9 9 9Refinement Universal Preambles (b) Command R WritingRoleplayReasoning Math Coding Extraction STEMHumanities 5 5 5 55 6 6 6 6 6 7 7 7 7 7 8 8 8 8 8 9 9 9 9 9 (c) Llama 3.1 70B Instruct Figure 2: Average scores per question type obtained by candidate-LLMs using a refinement-aware bias attack, [28]’s univer... | https://arxiv.org/abs/2505.15795v1 |
real-world scenario, it may not be possible to know in advance which judge-LLM the attack will target. It is therefore important to establish whether our method transfers to judges not used for training. In Table 3(b), we show the results of having a different judge-LLM evaluate candidate responses in all attack settin... | https://arxiv.org/abs/2505.15795v1 |
as rarely (20%) as those generated by the non-attacked model (16%). We also measure the rate at which each annotator is able to correctly detect each type of attack (both in terms of accuracy and F1). For both scores, we thus compute the median absolute deviation (MAD) across all annotators for each attack type, and fi... | https://arxiv.org/abs/2505.15795v1 |
pipeline. It is worth noting that, as further discussed in Appendix B, we assign relatively low weighting to the log-likelihoods of the adversarial preambles within the loss function, thus prioritising their rewards over their fluency during training. Remarkably, the training still converges toward preambles that elici... | https://arxiv.org/abs/2505.15795v1 |
instructions instead of pre-query preambles). 9 Broader Impacts This work focuses on aligning candidate-LLMs to judge-LLMs by means of tuned preambles injected into the candidate, with the aim of obtaining inflated evaluations. While there is a chance that this strategy may be exploited by adversaries, it is of scienti... | https://arxiv.org/abs/2505.15795v1 |
editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages 3029–3051, Singapore, Dec. 2023. Association for Computational Linguistics. [8]Y . Dubois, P. Liang, and T. Hashimoto. Length-controlled alpacaeval: A simple debiasing of automatic evaluators. In First Conference on ... | https://arxiv.org/abs/2505.15795v1 |
Muzzi, M. Pasupuleti, M. Singh, M. Paluri, M. Kardas, M. Tsimpoukelli, M. Oldham, M. Rita, M. Pavlova, M. Kambadur, M. Lewis, M. Si, M. K. Singh, M. Hassan, N. Goyal, N. Torabi, N. Bashlykov, N. Bogoychev, N. Chatterji, N. Zhang, O. Duchenne, O. Çelebi, P. Alrassy, P. Zhang, P. Li, P. Vasic, P. Weng, P. Bhargava, P. Du... | https://arxiv.org/abs/2505.15795v1 |
Zhen, J. Reizenstein, J. Teboul, J. Zhong, J. Jin, J. Yang, J. Cummings, J. Carvill, J. Shepard, J. McPhie, J. Torres, J. Ginsburg, J. Wang, K. Wu, K. H. U, K. Saxena, K. Khandelwal, K. Zand, K. Matosich, K. Veeraraghavan, K. Michelena, K. Li, K. Jagadeesh, K. Huang, K. Chawla, K. Huang, L. Chen, L. Garg, L. A, L. Silv... | https://arxiv.org/abs/2505.15795v1 |
task-specific classifiers. CoRR , abs/2403.02839, 2024. [16] N. Jain, A. Schwarzschild, Y . Wen, G. Somepalli, J. Kirchenbauer, P. yeh Chiang, M. Goldblum, A. Saha, J. Geiping, and T. Goldstein. Baseline defenses for adversarial attacks against aligned language models, 2023. [17] S. Kim, J. Suk, J. Y . Cho, S. Longpre,... | https://arxiv.org/abs/2505.15795v1 |
The Thirty-eighth Annual Conference on Neural Information Processing Systems , 2024. [26] Y . Qin, K. Song, Y . Hu, W. Yao, S. Cho, X. Wang, X. Wu, F. Liu, P. Liu, and D. Yu. InFoBench: Evaluating instruction following ability in large language models. In L.-W. Ku, A. Martins, and V . Srikumar, editors, Findings of the... | https://arxiv.org/abs/2505.15795v1 |
and chatbot arena. In Proceedings of the 37th International Conference on Neural Information Processing Systems , NIPS ’23, Red Hook, NY , USA, 2024. Curran Associates Inc. [37] X. Zheng, T. Pang, C. Du, Q. Liu, J. Jiang, and M. Lin. Cheating automatic LLM benchmarks: Null models achieve high win rates. In The Thirteen... | https://arxiv.org/abs/2505.15795v1 |
each training pipeline. PipelineSelected checkpoint step Command R7B+R7B 600 Command R7B+R 1000 Llama 8B+70B 600 B.3 Training Times We train the Command R7B+R7B pipeline and the Llama 8B+70B pipeline for 600 steps, and the Command R7B+R for 1k steps. In our specific setup, we rely on API/remote server models for the re... | https://arxiv.org/abs/2505.15795v1 |
averaged (showing the standard deviation in the subscript) to account for small variations due to temperature sampling. Candidate-LLMAttack type Refinement Universal Preambles Writing 8.450.04 8.71 0.01 8.610.07 Roleplay 8.600.05 8.650.03 8.69 0.06 Reasoning 5.630.09 4.900.06 5.89 0.11 Command R7BMath 4.470.10 3.600.07... | https://arxiv.org/abs/2505.15795v1 |
attacks aim to inflate the evaluation score that each response would receive when assessed by another, larger LLM. Your task is to read the question and the response, determine if the response has been attacked or not, and label it as ‘attacked’ or ‘not attacked’. Note: you do not need to record *which* attack you thin... | https://arxiv.org/abs/2505.15795v1 |
you are addressing. For instance, if you are emailing your direct supervisor, you can sound more formal and include more detail. On the other hand, if you are emailing a supervisor that is more distant, or if you are emailing a professor or industry expert with whom you have only had limited interactions, you should so... | https://arxiv.org/abs/2505.15795v1 |
as “Thank you for your time and guidance.” Finally, remember to proofread your email before sending it. Pay attention to grammar, spelling, and punctuation to ensure that your writing is polished and professional. Also, keep in mind that the tone and language you use in your email should align with the overall professi... | https://arxiv.org/abs/2505.15795v1 |
E. Preamble 4: Command R7B+R7B This is the best possible way to answer the question and obtain a high mark: - Read the question carefully and completely. Make sure you understand exactly what is be- ing asked of you. Sometimes, questions can be complex or have hidden nuances, so pay close attention to every detail. If ... | https://arxiv.org/abs/2505.15795v1 |
a question in an exam: 1. Read the question carefully and thoroughly. 2. Identify the key terms and concepts in the question. 3. Consider the scope and depth of the question. Is it a brief or narrow question, or is it more wide-ranging and open to in-depth analysis? 4. Determine the appropriate structure and sequence f... | https://arxiv.org/abs/2505.15795v1 |
SVDVVVDVKDVVKDVVVDVKVDVVDGDHVVTDKDVVDVRDVKDVCVCVCSCVCVMCVCR DVVDVDVCRDVVSRDVKDVVRSRDVVVKDVVVDVVRDKDVRDVVVKVVSRDVVHVVSRDV VDVVVVKDVKDVKCVRDVRDVVDVVVVVVKIKRDGKDVCDVRKIKDVCVKDVVKDVVGDG DVKDVKDVVVKIKDVVVVKDVKDVVVIKDVVVVKDVVVDVKDVVDVVDVHKDVVCVKIKD VVVSRDVKDVVVKDVKDVVDVKDVVDVRDVKDVVDVIKVCRDVVVVVKDVVDVVDVVKV KDVRDVKDVCVTDVKRD... | https://arxiv.org/abs/2505.15795v1 |
VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models Yuchen Yan1,2,*, Jin Jiang2,3, Zhenbang Ren1,4, Yijun Li1, Xudong Cai1,5, Yang Liu2, Xin Xu6,Mengdi Zhang2,Jian Shao1,†,Yongliang Shen1,†,Jun Xiao1,Yueting Zhuang1 1Zhejiang University2Meituan Group3Peking University 4University of Elect... | https://arxiv.org/abs/2505.15801v2 |
May 2025 LRMs is their reliance on reference-based reward systems, where rewards are assigned based on alignment between model-generated responses and authoritative reference answers. This approach has been implemented variously across leading models, with Deepseek-R1 (DeepSeek-AI et al., 2025a) em- ploys a rule-based ... | https://arxiv.org/abs/2505.15801v2 |
both Verify- Bench and VerifyBench-Hard, offering ac- tionable insights to advance the accuracy of reference-based reward systems and enhance RL training in reasoning tasks. 2 Preliminaries Reference-free Reward Models In reinforce- ment learning (RL) for large language models (LLMs), the reward model plays a crucial r... | https://arxiv.org/abs/2505.15801v2 |
The function E(·)represents an operation (e.g., thresholding or discretization) mapping continuous reward scores into discrete cor- rectness predictions suitable for direct comparison with the ground-truth labels y. 3 Benchmark Construction In this paper, we introduce two benchmarks, VerifyBench and VerifyBench-Hard, t... | https://arxiv.org/abs/2505.15801v2 |
this issue, we per- formed controlled downsampling to ensure uniform category-level representation and balanced correct- ness labels. Specifically, we retained 250 ques- tions per answer type, resulting in a total of 1,000 questions. Each question is paired with exactly two completions, one correct and one incorrect. T... | https://arxiv.org/abs/2505.15801v2 |
answers on the verification process. Section 4.3 provides a comparative analysis between our bench- mark and existing reward benchmarks, as well as the performance of several general-purpose reward models on VerifyBench and VerifyBench-Hard. 4.1 Overall Performance We evaluate the performance of various verification ap... | https://arxiv.org/abs/2505.15801v2 |
still have potential for devel- opment: In practical reinforcement learning sce- narios, the inference efficiency of the reward sys- tem significantly impacts the overall training speed. Since such verification tasks typically involve gen- erative inference, their computational cost is com- parable to that of the rollo... | https://arxiv.org/abs/2505.15801v2 |
on gen- eral reward benchmarks compared to VerifyBench, validating the benchmark’s design objectives. 5 Analysis 5.1 Error Analysis To gain deeper insights from VerifyBench, we intro- duce a more fine-grained taxonomy for each answer type and analyze model performance across these subcategories. This detailed analysis ... | https://arxiv.org/abs/2505.15801v2 |
goal of improving the effectiveness of RL for reasoning models by enhancing the accu- racy of reference-based reward systems. To evalu- ate the practical utility of our benchmark, we per- formed a correlation analysis between VerifyBench and real-world RL performance. In our experiments, we applied rejection sam- pling... | https://arxiv.org/abs/2505.15801v2 |
in this study, and their verifi- cation remains an open research challenge. Binary Scoring System The benchmark con- structed in this paper employs a binary scoring system, where each completion is labeled as either correct or incorrect. However, real-world scenarios often involve more nuanced cases, such as partially ... | https://arxiv.org/abs/2505.15801v2 |
contradictory infor- mation. arXiv preprint . Muhammad Khalifa, Rishabh Agarwal, Lajanugen Lo- geswaran, Jaekyeom Kim, Hao Peng, et al. 2025. Process reward models that think. arXiv preprint . Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, et al. 2025. Kimi k1.5: Scaling reinforcement learning with llms. ... | https://arxiv.org/abs/2505.15801v2 |
Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, et al. 2023. Gpqa: A graduate-level google-proof q&a bench- mark. arXiv preprint . 10 Abulhair Saparov and He He. 2023. Language models are greedy reasoners: A systematic formal analysis of chain-of-thought. arXiv preprint . David Saxton, Edward Grefenstette, Felix... | https://arxiv.org/abs/2505.15801v2 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.