text string | source string |
|---|---|
bibliography, one on each line. Copy the references verbatim. Respond only with the list of references, no other text. Do not include bullet points or numbered lists, but edit the formatting so each citation fits on exactly one line. Do not include parenthetical citations. Just focus on the bibliography section. A.2 Fe... | https://arxiv.org/abs/2505.15948v1 |
10 Presented at the Workshop on Open Citations & Open Scholarly Metadata 2025 <mixed-citation publication-type="journal"><person-group person-group- type="author"><name name-style="western"><surname>Sagel</surname> <given-names>Z</given-names></name>, <name name- style="western"><surname>Tutluer</surname> <given- names... | https://arxiv.org/abs/2505.15948v1 |
Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey Chih-Kai Yang1, Neo S. Ho, Hung-yi Lee2 National Taiwan University 1chihkaiyang1124@gmail.com ,2hungyilee@ntu.edu.tw /githubhttps://github.com/ckyang1124/LALM-Evaluation-Survey Abstract With advancements in large audio-language models (L... | https://arxiv.org/abs/2505.15957v2 |
for their models or to pinpoint the field’s progress. Therefore, a structured overview of LALM evaluation frameworks is needed. This paper presents a comprehensive survey of LALM evaluation frameworks and introduces a tax- onomy categorizing evaluation dimensions. To the best of our knowledge, this is the first in-dept... | https://arxiv.org/abs/2505.15957v2 |
empha- sis on specific parts of the input utterance. This evaluates LALMs’ ability to capture and maintain fine-grained prosodic features. These benchmarks highlight challenges in fine- grained auditory awareness among current models, underscoring the need for improved modeling of subtle acoustic and paralinguistic inf... | https://arxiv.org/abs/2505.15957v2 |
includes LLM- as-a-judge (Gu et al., 2024) for scalable, automatic evaluation of open-ended responses (Huang et al.,2025a; Yang et al., 2024c; Wang et al., 2025a). Despite achieving promising results in certain areas, these benchmarks demonstrate that current LALMs still fall short of universally robust per- formance a... | https://arxiv.org/abs/2505.15957v2 |
et al., 2025). Overall, there remains substantial room to improve LALMs’ auditory ex- pertise and factual knowledge.4.3 Reasoning Reasoning over auditory inputs falls into two types. Content-based reasoning tests a model’s ability to understand spoken semantic content and answer questions. Acoustic-based reasoning requ... | https://arxiv.org/abs/2505.15957v2 |
reasoning, even when both types of information are extracted and known by the models. 5 Dialogue-oriented Ability While foundational skills such as auditory aware- ness (§3.1), fundamental processing (§3.2), language proficiency (§4.1), advanced knowl- edge (§4.2), and reasoning (§4.3) are essential for LALMs, natural ... | https://arxiv.org/abs/2505.15957v2 |
be inaccurate in some cases. Their results show that LALMs struggle with full-duplex management, especially with interrup- tions (Arora et al., 2025b) and seamless turn transi- tions (Lin et al., 2025a), highlighting current limi- tations in dynamic spoken interaction. 5.2 Instruction Following Instruction following is... | https://arxiv.org/abs/2505.15957v2 |
indicators (e.g., “mother”) removed to ensure bias would be triggered by speaker characteristics rather than content. The modified sentences were synthesized into speech using TTS with voices of different genders and ages. These spoken sentences served as the con- text, and LALMs were tasked with selecting contin- uati... | https://arxiv.org/abs/2505.15957v2 |
to incorrectly predict their presence, even when they are absent. Additionally, the frequent co-occurrence of objects and events during training exacerbates these hallucinations. These works highlight hallucination challenges in LALMs and call for improved training, model- ing, and data handling to enhance trustworthin... | https://arxiv.org/abs/2505.15957v2 |
et al., 2024), where vocal manner greatly affects user trust and comfort. Future work should jointly consider vocal tone, noise, and other paralinguistic factors to ensure safe, user-friendly interactions. 7.4 Unified Evaluation of Harmlessness and Helpfulness Harmlessness and helpfulness in LALMs refer to safety and f... | https://arxiv.org/abs/2505.15957v2 |
to evaluate LALMs’ per- formance across various aspects. As a result, it does not put much emphasis on more basic or tra- ditional evaluation methods, such as subjective as- sessments of speech generation quality (e.g., Mean Opinion Score), which are commonly used to eval- uate model-generated audio. While these method... | https://arxiv.org/abs/2505.15957v2 |
sociation for Computational Linguistics. Fan Bu, Yuhao Zhang, Xidong Wang, Benyou Wang, Qun Liu, and Haizhou Li. 2024. Roadmap towards superhuman speech understanding using large lan- guage models. arXiv preprint arXiv:2410.13268 . Hui Bu, Jiayu Du, Xingyu Na, Bengu Wu, and Hao Zheng. 2017. Aishell-1: An open-source ma... | https://arxiv.org/abs/2505.15957v2 |
Spoken Language Technology Workshop (SLT) , pages 798–805. IEEE. Joris Cosentino, Manuel Pariente, Samuele Cornell, Antoine Deleforge, and Emmanuel Vincent. 2020. Librimix: An open-source dataset for generalizable speech separation. arXiv preprint arXiv:2005.11262 . Wenqian Cui, Xiaoqi Jiao, Ziqiao Meng, and Irwin King... | https://arxiv.org/abs/2505.15957v2 |
Stephen C Levinson. 2009. The myth of language universals: Language diversity and its importance for cognitive science. Behavioral and brain sciences , 32(5):429–448. Y . Fan, J.W. Kang, L.T. Li, K.C. Li, H.L. Chen, S.T. Cheng, P.Y . Zhang, Z.Y . Zhou, Y .Q. Cai, and D. Wang. 2020. Cn-celeb: A challenging chinese speak... | https://arxiv.org/abs/2505.15957v2 |
ICASSP 2022-2022 IEEE Interna- tional Conference on Acoustics, Speech and Signal Processing (ICASSP) , pages 151–155. IEEE. Jesse Graham, Peter Meindl, Erica Beall, Kate M John- son, and Li Zhang. 2016. Cultural differences in moral judgment and behavior, across and within soci- eties. Current Opinion in Psychology , 8... | https://arxiv.org/abs/2505.15957v2 |
pages 12136–12140. Chien-yu Huang, Min-Han Shih, Ke-Han Lu, Chi- Yuan Hsiao, and Hung-yi Lee. 2025b. Speech- caps: Advancing instruction-based universal speech models with multi-talker speaking style captioning. InICASSP 2025-2025 IEEE International Confer- ence on Acoustics, Speech and Signal Processing (ICASSP) , pag... | https://arxiv.org/abs/2505.15957v2 |
Heeseung Kim, Che Hyun Lee, Sangkwon Park, Ji- heum Yeom, Nohil Park, Sangwon Yu, and Sungroh Yoon. 2025. Does your voice assistant remember? analyzing conversational context recall and utiliza- tion in voice interaction models. arXiv preprint arXiv:2502.19759 . Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yu- taka ... | https://arxiv.org/abs/2505.15957v2 |
large language models to cap- ture varied speaking styles and respond properly in spoken conversations. In Proceedings of the 62nd An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages 6626– 6642. Guan-Ting Lin, Jiachen Lian, Tingle Li, Qirui Wang, Gopala Anumanchipalli, Alex... | https://arxiv.org/abs/2505.15957v2 |
Natural Language Processing (Volume 1: Long Papers) , pages 5356–5371. Tu Anh Nguyen, Maureen de Seyssel, Patricia Rozé, Morgane Rivière, Evgeny Kharitonov, Alexei Baevski, Ewan Dunbar, and Emmanuel Dupoux. 2020. The zero resource speech benchmark 2021: Metrics and baselines for unsupervised spoken lan- guage modeling.... | https://arxiv.org/abs/2505.15957v2 |
arXiv preprint arXiv:2504.01094 .Harvey Sacks, Emanuel A Schegloff, and Gail Jefferson. 1974. A simplest systematics for the organization of turn-taking for conversation. language , 50(4):696– 735. S Sakshi, Utkarsh Tyagi, Sonal Kumar, Ashish Seth, Ramaneswaran Selvakumar, Oriol Nieto, Ramani Du- raiswami, Sreyan Ghosh... | https://arxiv.org/abs/2505.15957v2 |
dataset for spoken language recognition. In 2021 IEEE Spoken Language Technology Workshop (SLT) , pages 652–658. IEEE. Christophe Veaux, Junichi Yamagishi, Kirsten MacDon- ald, and 1 others. 2017. Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit. University of Edinburgh. The Centre for Spee... | https://arxiv.org/abs/2505.15957v2 |
(SLT) , pages 1137–1143. IEEE. Erjia Xiao, Hao Cheng, Jing Shao, Jinhao Duan, Kaidi Xu, Le Yang, Jindong Gu, and Renjing Xu. 2025. Tune in, act up: Exploring the impact of audio modality-specific edits on large audio language mod- els in jailbreak. arXiv preprint arXiv:2501.13772 . Liumeng Xue, Ziya Zhou, Jiahao Pan, Z... | https://arxiv.org/abs/2505.15957v2 |
Music audio representation benchmark for universal evaluation. Advances in Neural Information Process- ing Systems , 36:39626–39647. Yongyi Zang, Sean O’Brien, Taylor Berg-Kirkpatrick, Julian McAuley, and Zachary Novack. 2025. Are you really listening? boosting perceptual aware- ness in music-qa benchmarks. arXiv prepr... | https://arxiv.org/abs/2505.15957v2 |
2024); RUListening (Zang et al., 2025); OpenMU-Bench (Zhao et al., 2024); Reasoning (§4.3)CompA (Ghosh et al., 2024b); MMAU (Sakshi et al., 2025); SAKURA (Yang et al., 2025a); URO-Bench (Yan et al., 2025); Audio Entailment (Deshmukh et al., 2025a); Wang et al. (2025d); ADU-Bench (Gao et al., 2024); VoxEval (Cui et al.,... | https://arxiv.org/abs/2505.15957v2 |
Classification V ocalSound (Gong et al., 2022) Speech Tasks Automatic Speech RecognitionLibriSpeech (Panayotov et al., 2015b) AISHELL-1 (Bu et al., 2017) Common V oice (Ardila et al., 2020) Speaker IdentificationV oxCeleb2 (Chung et al., 2018) CN-Celeb (Fan et al., 2020) Text-to-SpeechLJSpeech (Ito and Johnson, 2017) V... | https://arxiv.org/abs/2505.15957v2 |
and Reasoning (§4), Dialogue-oriented Abil- ity (§5), and Fairness, Safety, and Trustworthi- ness (§6), respectively. These tables are compiled based on the original papers of the surveyed bench- marks. Please note that due to unique evaluation designs, some benchmarks do not produce explicit “outputs” but instead rely... | https://arxiv.org/abs/2505.15957v2 |
RUListening (Zang et al., 2025) ✓ ✓ ✓ OpenMU-Bench (Zhao et al., 2024) ✓ ✓ ✓ Gong et al. (2024a) ✓ ✓ ✓ ✓ ✓ CompA-R (Ghosh et al., 2024a) ✓ ✓ ✓ OpenAQA (Gong et al., 2024b) ✓ ✓ ✓ Clotho-AQA (Lipping et al., 2022) ✓ ✓ ✓ SLU-GLUE (Li et al., 2024) ✓ ✓ ✓ SpeechCaps (Huang et al., 2025b) ✓ ✓ ✓ Wang et al. (2025d) ✓ ✓ ✓ ✓ De... | https://arxiv.org/abs/2505.15957v2 |
arXiv:2505.15960v1 [cs.CL] 21 May 2025Training Step-Level Reasoning Verifiers with Formal Verification Tools Ryo Kamoi Yusen Zhang Nan Zhang Sarkar Snigdha Sarathi Das Rui Zhang Penn State University {ryokamoi, rmz5227}@psu.edu Abstract Process Reward Models (PRMs), which provide step-by-step feedback on the reasoning ... | https://arxiv.org/abs/2505.15960v1 |
FOVERsignificantly improves verification performance on broad out-of-distribution reasoning tasks, compared to baseline PRMs based on the original LLMs. Details are in Table 3. 1 Introduction Reasoning verifiers for large language models (LLMs) have been increasingly studied in the context of enhancing the reasoning ca... | https://arxiv.org/abs/2505.15960v1 |
original LLMs, as measured in the two settings. Surprisingly, our experiments on 12 reasoning benchmarks show that training on our dataset—comprising of error labels on formal logic and theorem proof tasks—enhances Best-of-K performance of LLM-based PRMs across diverse reasoning tasks, including MATH [ 11], AIME [ 2], ... | https://arxiv.org/abs/2505.15960v1 |
is a primary approach, but is particularly costly in this step-level labeling task. Recent studies explore synthetic annotations, such as rule-based or model-based perturbations [ 60, 23,33] and Monte Carlo roll-outs [ 50,22,65]. However, these approaches can produce unnatural or inaccurate step-level error labels. In ... | https://arxiv.org/abs/2505.15960v1 |
= 150 dollars. He wants to make a profit of 100 dollars, so [...]LLMInformal Question Informal Solution assumes "(total_pencils::nat) = 1500" and "(cost_per_pencil::real) = 0.10" and "(sell_price_per_pencil::real) = 0.25" [...] shows "pencils_to_sell = 1000" Conversion LLMFormal Statement Formal ProofConversion LLM The... | https://arxiv.org/abs/2505.15960v1 |
simple. In the formal theorem proof task, we generate informal reasoning from the LLMs and convert it to a formal format using stronger LLMs (Figure 3b) because Isabelle’s format is too complex to follow for the relatively small LLMs we use. (2) Second, we acquire step-level error labels using formal verification tools... | https://arxiv.org/abs/2505.15960v1 |
implement code for step-level verification, based on an existing library for verifying Isabelle proofs [ 54]. Specifically, our code assumes that the other steps are correct and evaluates whether the target step is valid. Refer to Appendix F.3 for details. 5 4 Experiments We evaluate our PRMs trained on the FOVERdatase... | https://arxiv.org/abs/2505.15960v1 |
evaluating training methodologies, as it offers limited insight into improving PRMs built on top of state-of-the-art LLMs—in settings where stronger models for annotation are unavailable. In contrast, we train LLM-based PRMs using labels from formal verification tools on their own responses, avoiding distilling any cap... | https://arxiv.org/abs/2505.15960v1 |
2.5 7B 90.4 64.4 79.5 12.0 62.1 46.8 32.0 84.8 58.8 90.0 89.2 28.8 61.6 Qwen2.5-7B-Skywork-PRMµ?96.0∗68.8∗78.0 13.6 62.6 44.8 30.0 82.0 60.0 82.4 90.8 30.8 61.6 Qwen2.5-Math-7B-PRM800Kµ†94.8∗68.8∗81.1 13.2 66.5∗47.6 34.0 83.6 58.8 81.6 90.4 28.4 62.4 Qwen2.5-Math-PRM-7Bµ‡94.8∗69.2∗82.7 15.2∗65.5 48.8 28.0 84.8 58.4 84.... | https://arxiv.org/abs/2505.15960v1 |
on Qwen 2.5 7B select the best response from K= 5 responses generated by Qwen 2.5 7B ✓ – 92.8∗65.2 81.1 10.8 61.6 46.8 31.2 87.2∗61.2 90.8 89.2 32.8∗62.6∗ – ✓ 91.6 66.0 81.5 12.4 62.1 50.4 32.0 84.0 60.4 91.6 90.8 30.4 62.8∗ ✓ ✓ 92.8∗66.4 82.3 13.2 65.5 48.8 32.4 85.2 60.8 91.6 89.6 31.2 63.3∗ Table 6: Ablation study o... | https://arxiv.org/abs/2505.15960v1 |
where FOVERimproves or degrades re-ranking in Best-of-K from baseline PRMs (§4.1). As Best-of-K evaluates the final answers of selected solutions 8 Table 7: Verification of an LLM response to MMLU-Pro-NoMath by PRMs based on Llama 3.1 8B. FOVERPRM improves the scores from the baseline and successfully detects the wrong... | https://arxiv.org/abs/2505.15960v1 |
tasks. As in Figure 7, problems in this dataset require complex reasoning and domain knowledge to verify solutions. In this example, FOVERPRM correctly understands the concept of “absolutism” in Step 0 and detects a logical mistake in Step 1. Although the FOVERdataset does not include knowledge-intensive tasks, it make... | https://arxiv.org/abs/2505.15960v1 |
March 2008. URL https: //www.microsoft.com/en-us/research/publication/z3-an-efficient-smt-solver/ . [8]Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell... | https://arxiv.org/abs/2505.15960v1 |
URL https://openreview.net/forum? id=IFXTZERXdM7 . [17] Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. Making language models better reasoners with step-aware verifier. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the... | https://arxiv.org/abs/2505.15960v1 |
12–15, 2021, Proceedings , page 625–635, Berlin, Heidelberg, 2021. Springer-Verlag. ISBN 978-3-030-79875-8. doi: 10.1007/978-3-030-79876-5_37. URL https://doi.org/10.1007/ 978-3-030-79876-5_37 . [29] Yixin Nie, Adina Williams, Emily Dinan, Mohit Bansal, Jason Weston, and Douwe Kiela. Adversarial NLI: A new benchmark fo... | https://arxiv.org/abs/2505.15960v1 |
Processing Systems , volume 30. Curran As- sociates, Inc., 2017. URL https://proceedings.neurips.cc/paper_files/paper/2017/file/ 0efbe98067c6c73dba1250d2beaa81f9-Paper.pdf . [43] Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. Scaling llm test-time compute optimally can be more effective than scaling model par... | https://arxiv.org/abs/2505.15960v1 |
Nan Du, Andrew M. Dai, and Quoc V Le. Finetuned language models are zero-shot learners. In International Conference on Learning Representations , 2022. URL https://openreview.net/forum?id=gEZrGCozdqR . [54] Sean Welleck. Neural theorem proving tutorial. https://github.com/wellecks/ntptutorial , 2023. 13 [55] Yuhuai Wu,... | https://arxiv.org/abs/2505.15960v1 |
Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. Processbench: Identifying process errors in mathematical reasoning. In The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) (to appear) , 2025. [67] Yaowei Zheng, Richon... | https://arxiv.org/abs/2505.15960v1 |
. . . . . . 25 G Input Format and Postprocessing for LLM-based PRMs 28 G.1 Input Format . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 G.2 Postprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 G.3 Existing PRMs . . . . . . . . . . . . . . . . . . . . . .... | https://arxiv.org/abs/2505.15960v1 |
of source tasks for our training data. Our training data in this project targets improving PRMs based on 8B-class LLMs and includes tasks that may not be difficult for larger state-of-the-art LLMs, such as GSM8K-level math reasoning tasks in the formal theorem proof task. When applying our approach to improve PRMs base... | https://arxiv.org/abs/2505.15960v1 |
we evaluate in Section 4.1. PRMs Source Base Datasets Error Annotation RLHFlow-Llama3.1-8B-DeepSeek [59] RLHFlow/Llama3.1-8B-PRM-Deepseek-Data GSM8K, MATH Math-Shepherd [50] RLHFlow-Llama3.1-8B-Mistral [59] RLHFlow/Llama3.1-8B-PRM-Mistral-Data GSM8K, MATH Math-Shepherd [50] Qwen2.5-Math-7B-PRM800K [66] Qwen/Qwen2.5-Mat... | https://arxiv.org/abs/2505.15960v1 |
Stella_Artois_speed * total_time) / total_time" ,→ shows "first_car_speed = 145.2" ** Task ** Your task is to evaluate the accuracy of each step in the provided solution to the above question. For each step, respond with "correct" if the reasoning is logically valid and mathematically sound, or if the step is a general... | https://arxiv.org/abs/2505.15960v1 |
proof by contradiction. If the hypothesis is disproved, provide a direct counterexample. If the proof_label is PROVED, your proof should end with the 'hypothesis '. If the proof_label is DISPROVED, your proof should end with '¬hypothesis '.,→ ,→ ,→ $hypothesis$: ({AB}{c} & ¬{B}{c}) $context$: fact1: (x): ¬{D}x -> ({A}x... | https://arxiv.org/abs/2505.15960v1 |
your formal statement consistent with the provided Informal Statement. * The final answer can be wrong, but your formal statement should be faithful to the informal statement and should not correct the mistakes in the informal statement.,→ ,→ * You should not use new variables in "shows". * The "shows" part is expected... | https://arxiv.org/abs/2505.15960v1 |
for the cabin, how much money will Gloria have left?,→ ,→ ,→ ,→ ,→ Final Answer -- The answer is 200. ** Informal Proof ** Gloria needs 129,000 dollars for the cabin, but she only has 150 dollars. So she needs 129,000 - 150 = 128,850 dollars. She will get 100 dollars for each of the 20 cypress trees, which is 20 x 100 ... | https://arxiv.org/abs/2505.15960v1 |
(* So she needs 129,000 - 150 = 128,850 dollars. *) have "Cabin_cost - Gloria_cash = 128850" sledgehammer 24 (* She will get 100 dollars for each of the 20 cypress trees, which is 20 ×100 = 2,000 dollars. *) ,→ then have "Cypress_count * Cypress_price = 2000" sledgehammer (* She will get 300 dollars for each of the 24 ... | https://arxiv.org/abs/2505.15960v1 |
“sorry” into all generated proof steps, we can isolate and verify only the syntactic and semantic well-formedness of theorems. For example, if the following theorem gets errors from Isabelle, we can detect syntax errors and filter this theorem out from our dataset. In this case, the expression babysitting_minutes × (We... | https://arxiv.org/abs/2505.15960v1 |
solution to the above question. For each step, respond with "correct" if the reasoning is logically valid and mathematically sound, or if the step is a general statement or transition that does not contain reasoning. Respond with "incorrect" if the step includes any errors or flawed logic.,→ ,→ ,→ ,→ ,→ ** Sotluion ** ... | https://arxiv.org/abs/2505.15960v1 |
'error_labels ': [True, False, True, True, True], 'messages ': [ { 'role ':'user ', 'content ':'** Problem ** Generate a proof for the following theorem in the Isabelle proof assistant format. ,→ theorem example: assumes "(Stella_Artois_speed::real) = 150" and "(total_distance::real) = 500" and "(total_time::real) = 1.... | https://arxiv.org/abs/2505.15960v1 |
Exact match after extraction and conversion to integer FOLIO Made by us (2-shot) Exact match after extraction LogicNLI Made by us (3-shot) Exact match after extraction ANLI Made by us (3-shot) Exact match after extraction HANS Made by us (2-shot) Exact match after extraction MMLU Made by us (4-shot) Exact match after e... | https://arxiv.org/abs/2505.15960v1 |
impact on the transferability and that the optimal learning rate varies across models and evaluation tasks. Label distribution. We evaluate PRMs trained on FOVERwith varying proportions of correct and incorrect step-level labels. Specifically, we construct versions of the FOVERdataset that include both formal logic and... | https://arxiv.org/abs/2505.15960v1 |
incorrect ones. (b) F OVERPRMs select solutions with incorrect final answers while baseline PRMs select correct ones. Figure 6: Manual analysis of step-level scores in cases where FOVERPRMs improve (6a) or degrade (6b) re-ranking in Best-of-K with regard to the final answers. The blue and red areas represent the cases ... | https://arxiv.org/abs/2505.15960v1 |
truth answer is “neutral”. However, this problem is ambiguous, and both neutral and entailment are reasonable final answers. Therefore, this case does not represent a degradation by F OVER. Problem: Premise: Trying Tofu<br>Alicia was feeling a little adventurous. She wanted to try Tofu. She had never had it before. So ... | https://arxiv.org/abs/2505.15960v1 |
< farther < insolent < ping < protocol < raillery < stephen < tech.0.9961 0.7305 Solution-level Score 0.5938 0.1641 Solution selected by F OVERPRMs (wrong final answer) Step 0First, we look at the first letters of each word. "stephen": "s" (19th letter). "amperage": "a" (1st letter). "protocol": "p" (16th letter). "cri... | https://arxiv.org/abs/2505.15960v1 |
F OVERPRMs (wrong final answer) Step 0 Mark edits 1000 sentences each week. 0.9922 1.0000 Step 1Publisher A pays him 5 cents per sentence, so Publisher A pays him 1000 x 5 = 5000 cents per week.1.0000 0.9883 Step 2Since Publisher B pays twice what Publisher A pays, Publisher B pays 2 x 5000 = 10,000 cents per week.0.99... | https://arxiv.org/abs/2505.15960v1 |
licenses listed below. Datasets. Our training data is based on the following datasets. • FLDx2 [27]: Creative Commons Attribution 4.0 International8 • GSM8K [6]: MIT9 • MetaMathQA [62]: MIT10 • Big-Math [1]: Apache License 2.011 Code and packages. Our code is partially based on the following resources. • FLD [27]: Apac... | https://arxiv.org/abs/2505.15960v1 |
arXiv:2505.15962v1 [cs.CL] 21 May 2025Pre-training Large Memory Language Models with Internal and External Knowledge Linxi Zhao∗, Sofian Zalouk, Christian K. Belardi, Justin Lovelace, Jin Peng Zhou, Kilian Q. Weinberger ,Yoav Artzi ,Jennifer J. Sun Department of Computer Science Cornell University {lz586, saz43, ckb73,... | https://arxiv.org/abs/2505.15962v1 |
designed to both internalize knowledge and retrieve it from external sources. knowledge generalizes across contexts, making it well-suited for storage in the model’s parameters. Specific knowledge is non-generalizable: it appears in narrow contexts, does not transfer, and contributes disproportionately to the memorizat... | https://arxiv.org/abs/2505.15962v1 |
15, 1769 ] August 15, 1769.Annotated T ext: (Napoleon , Birth Date )→August 15, 1769Napoleon was born on August 15, 1769.Original T ext: Annotator Next token prediction with masked Return Value Special Tokens Entity Relation Return V alueFigure 2: Overview of the LMLMframework. Our framework consists of (Left) Data Pre... | https://arxiv.org/abs/2505.15962v1 |
externalize factual knowledge from raw pre-training text, enabling scalable annotation of the full corpus. 3 2.5 5.0 7.5 10.012.515.0 Pretrain Tokens (B)6789101112Normalized Eval PPL ↓ 382M176M382M176M LMLM Standard35 40 45 NLU Average Performance1015202530FactScore (%)↑ GPT2-124M∗GPT2-355M∗GPT2-774M∗ LLaMA2-176MLLaMA2... | https://arxiv.org/abs/2505.15962v1 |
similarity over ALL-MINILM-L6- V2 embeddings (with a rejection threshold of 0.6). Baseline Comparisons. We consider the following pre-training settings: • LMLM(Ours) : Pre-trained on our annotated data with lookup calls, using the loss in Equation (1). • STANDARD : Pre-trained on our data without lookup calls. All othe... | https://arxiv.org/abs/2505.15962v1 |
factual precision, while T-REx tests factual statement completion. Subscripts indicate the absolute difference compared to their respective S TANDARD baselines. FactScore (Open-ended Generation) T-REx (Knowledge Completion) Model Model Type FActScore ↑FActScore w/o len. penalty ↑# Facts / Response ↑Exact Match ↑ Precis... | https://arxiv.org/abs/2505.15962v1 |
the LM to extract relevant information implicitly. In contrast, LMLMis trained end-to-end to issue structured lookup calls only when factual retrieval is needed, interleaving retrieval and generation at the entity level. This makes LMLMmore precise and efficient: it avoids unnecessary retrievals, reduces token overhead... | https://arxiv.org/abs/2505.15962v1 |
ROUGE (answer quality), Answer Probability , and Truth Ratio (likelihood assigned to the correct answer over distractors)—measured on the Retain Set, Real Author Set, and World Facts Set. •Forget quality: Thep-value of a statistical test comparing the unlearned model with the correspond- ing retain model to assess whet... | https://arxiv.org/abs/2505.15962v1 |
internally. LMLM’s successful application in the machine unlearning benchmark (Sec. 3.4) further supports this finding. Additionally, we observe a notable performance gap in Table 3, where factual precision drops substantially when the external database is disabled—forcing the model to rely on its internal parameters. ... | https://arxiv.org/abs/2505.15962v1 |
even when excluding certain sources from pretraining, competitive perplexity can be maintained through proper retrieval mechanisms. Semi-parametric language models aim to decouple knowledge storage from generation by attaching non-parametric memories of key-value pairs. A prominent example is kNN-LM [ 27], which retrie... | https://arxiv.org/abs/2505.15962v1 |
partially supported by LinkedIn-Cornell Partnership, Open Philantropy, the National Science Foundation NSF (IIS-2107161, and IIS-1724282, HDR-2118310), the Cornell Center for Materials Research with funding from the NSF MRSEC program (DMR-1719875), DARPA, arXiv, and the New York Presbyterian Hospital. 10 References [1]... | https://arxiv.org/abs/2505.15962v1 |
Simplicity prevails: Rethinking negative preference optimization for llm unlearning, 2025. URL https://arxiv.org/abs/2410.07163 . [16] Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Shi Jie, Xiang Wang, Xiangnan He, and Tat seng Chua. Alphaedit: Null-space constrained knowledge editing for language models, 2025. U... | https://arxiv.org/abs/2505.15962v1 |
Ruochen Xu, Chen Lin, Yujiu Yang, Jian Jiao, Nan Duan, and Weizhu Chen. Rho-1: Not all tokens are what you need, 2025. URLhttps://arxiv.org/abs/2404.07965 . [32] Bo Liu, Qiang Liu, and Peter Stone. Continual learning and private unlearning, 2022. URL https://arxiv.org/abs/2203.12817 . [33] Pratyush Maini, Zhili Feng, A... | https://arxiv.org/abs/2505.15962v1 |
Liang. Know what you don’t know: Unanswerable questions for squad, 2018. URL https://arxiv.org/abs/1806.03822 . [49] Maarten Sap, Hannah Rashkin, Derek Chen, Ronan LeBras, and Yejin Choi. Socialiqa: Com- monsense reasoning about social interactions, 2019. URL https://arxiv.org/abs/1904. 09728 . [50] Timo Schick, Jane D... | https://arxiv.org/abs/2505.15962v1 |
( r=32 ,alpha=16 ) [20] for 2 epochs on 19k GPT-4o- annotated SQuAD-v2 passages, with a learning rate of 2×10−4and an effective batch size of 32. Sequence packing is enabled to improve training efficiency. •The ANNOTATOR is tuned with instruction on the 2k annotated passages using LoRA ( r=32 , alpha=16 ), with a learn... | https://arxiv.org/abs/2505.15962v1 |
factual knowledge should be externalized and how to issue structured lookup queries. The trained model is then applied to the full pre-training corpus to generate large-scale factual supervision. Prompt template is provided in Table 4. Additional Notes. We observe a bimodal loss distribution on entity and relation toke... | https://arxiv.org/abs/2505.15962v1 |
point for the returned value; –<|db_end|> : marks the end of the lookup block. Here is an example using background color to highlight different token categories: Torg: Napoleon was born on <|db_start|> Napoleon <|sep|> Birth_Date <|db_retrieve|> August 15, 1769 <|db_end|> August 15, 1769. Itrain: Napoleon was born on <... | https://arxiv.org/abs/2505.15962v1 |
we use a fixed prompt template to elicit biography completions: “ Tell me a bio of <name>. <name> is ” This prompt is applied consistently across all samples. To encourage structured queries during generation, we apply a logit bias to four special tokens in the vocabulary: <|db_start|> ,<|sep|> ,<|db_retrieve|> , and<|... | https://arxiv.org/abs/2505.15962v1 |
60] is a state-of-the-art method for selective knowledge removal, especially effective for unlearning large portions (50%-90%) of training data. Unlike traditional gradient-based unlearning methods, which often degrade a model’s general performance and struggle to forget only 10% of training data, NPO explicitly guides... | https://arxiv.org/abs/2505.15962v1 |
post-unlearning results. Details on how to interpret the results are in Appendix B.2. •Figure 7 : We use the TOFU synthetic training set to compare training objectives by tracking the loss on return value tokens—the factual spans intended to be retrieved via lookup. Models are evaluated every 125 steps during training.... | https://arxiv.org/abs/2505.15962v1 |
The database spans a wide range of entity frequencies, including many long-tail cases. D Further Analysis D.1 Does L MLMAffect Language Understanding? Beyond the promising results, it is important to verify that our approach does not compromise the general capabilities of pretrained language models. To assess this, we ... | https://arxiv.org/abs/2505.15962v1 |
queries. In contrast, prefix-tree decoding restricts generation to valid entries encoded in a trie structure, ensuring syntactic correctness and reducing hallucinations. It is also compatible with beam search and nucleus sampling, allowing the model to explore multiple valid paths in the induced knowledge graph. See Ap... | https://arxiv.org/abs/2505.15962v1 |
This castle later fell into disrepair during the Edo Period, and 24 Table 12: Qualitative examples of generated outputs from models with STANDARD andLMLM settings. Model Generated Output LLAMA2-382M - LMLMKo Itakura is the <|db_entity|> Ko Itakura<|db_relationship|> Position<|db_return|> center-back, defensive midfield... | https://arxiv.org/abs/2505.15962v1 |
to fight against Nazi Germany’s forces under General Yamamoto at Kure Castle near Tokyo. After defeating them all except one—Genosha-Kaiji from Earth Kingdom fame—they return home with their families but find that there was no sign left behind by those killed fighting alongside them; instead it seems like everything ha... | https://arxiv.org/abs/2505.15962v1 |
14: Example of input and output from the RAG model. The model is prompted using retrieved documents and a user query. Field Content Prompt Template Answer the question or complete the prompt based on the given document. The following are given documents: [RETRIEVED_DOCUMENTS] \n [USER_QUERY] Retrieved Documents "Kang J... | https://arxiv.org/abs/2505.15962v1 |
arXiv:2505.15963v1 [cs.CV] 21 May 2025OViP: Online Vision-Language Preference Learning Shujun Liu∗ Fudan UniversitySiyuan Wang University of Southern CaliforniaZejun Li Fudan University Jianxiang Wang ByteDanceCheng Zeng ByteDanceZhongyu Wei Fudan University Abstract Large vision-language models (LVLMs) remain vulnerab... | https://arxiv.org/abs/2505.15963v1 |
LLMFigure 1: Offline training (a) relies on static, predefined datasets and fails to adapt to the model’s evolving failure patterns, limiting its ability to address hallucinations effectively. Moreover, neglecting the role of visual input will result in overfitting to language priors. In contrast, OViP (b) combines onl... | https://arxiv.org/abs/2505.15963v1 |
duck's beak is white. The duck's beak is white with red stripes. ……2 Score𝑟𝑖 The duck in the image has a white beak. The contrast …… The duck's beak is white. The duck's beak is orange.1. Sample 2. Evaluate 4. Generate5. Online training G.T.𝝅𝒕8 6……LLM reference3. Filter𝝉=𝐦𝐚𝐱(𝜹,𝟐𝝈𝒓)Calculate standard deviati... | https://arxiv.org/abs/2505.15963v1 |
each set of candidate responses {Ai}k i=1with corresponding rewards {ri}k i=1, we compute the standard deviation σrof the reward scores and select pairs (A+,A−)that satisfy: |r+−r−|>max ( δ,2σr) 3 where δis a fixed lower-bound margin. This criterion ensures that only response pairs exhibiting substantial contrast in re... | https://arxiv.org/abs/2505.15963v1 |
image-free term πθ(A|Q)and implement the image-side loss as in [20]: LImage (I+,I−;Q,A+) =−logσ β1· logπθ(A+|I+,Q) πref(A+|I+,Q)−logπθ(A+|Q) πref(A+|Q) +β2· logπθ(A+|Q) πref(A+|Q)−logπθ(A+|I−,Q) πref(A+|I−,Q) (5) The overall loss function is then defined as: LOViP Q,I+,I−,A+,A− =LText A+,A−;I,Q +LImage I+,I−... | https://arxiv.org/abs/2505.15963v1 |
images from real-world and abstract scenarios. The evaluation is conducted using gpt-4o-2024-05-13 . •AMBER discriminative (AMBER dis) [34] includes 14,216 “Yes/No” questions regarding objects in image. We use the F1-score as its metrics. To aggregate performance across five hallucination-related benchmarks, we introdu... | https://arxiv.org/abs/2505.15963v1 |
+0.85 OViP 2ep 3.6 53.7 68.98 2.57 28.62 76.75 67.90 90.2 8.02 +2.02 and general visual capability, i.e., hallucination-targeted models often exhibit performance declines on non-hallucination benchmarks. To assess this impact, we further evaluate LVLMs’ capabilities on general benchmarks, including RealworldQA [ 36], T... | https://arxiv.org/abs/2505.15963v1 |
Specifically, we conduct experiments under two training regimes: (1) training from scratch, and (2) iterative training initialized with a DPO-pretrained model using the existing dataset, to ablate these losses on top of different initialized models with varying capabilities. As shown in Table 2, The full OViP loss cons... | https://arxiv.org/abs/2505.15963v1 |
ent training strategy. Offline represents training with existing dataset. Off Policy means train- ing with sampled data and Iter- ative means the dataset of the epoch 2 is from model sampling. (y) yHallucination suppression High-quality promotion Hallucination areaOnline DPO Offline DPO Base Model(y) y Positive distrib... | https://arxiv.org/abs/2505.15963v1 |
crafting counterfactual images to probe specific failure modes. Other works take a generative perspective: SynthVLM [ 43] and SynthEmbedding [ 44] utilize off-the-shelf models to synthesize new images or directly generate image embeddings for hallucination-aware training. Meanwhile, a larger body of research focuses on... | https://arxiv.org/abs/2505.15963v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.