English
Related papers

Related papers: Mitigating Legibility Tax with Decoupled Prover-Ve…

200 papers

Verifiers are crucial components for enhancing modern LLMs' reasoning capability. Typicalverifiers require resource-intensive superviseddataset construction, which is costly and faceslimitations in data diversity. In this paper, wepropose…

Computation and Language · Computer Science 2026-05-08 Xinyu Wang , Changzhi Sun , Lian Cheng , Yuanbin Wu , Dell Zhang , Xiaoling Wang , Xuelong Li

As Machine Learning (ML) systems becomes more ubiquitous, ensuring the fair and equitable application of their underlying algorithms is of paramount importance. We argue that one way to achieve this is to proactively cultivate public…

Computers and Society · Computer Science 2020-04-22 Eric Chu , Nabeel Gillani , Sneha Priscilla Makini

Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that get correct answers by chance. We observe that better…

Machine Learning · Computer Science 2026-03-11 Tiehua Mei , Minxuan Lv , Leiyu Pan , Zhenpeng Su , Hongru Hou , Hengrui Chen , Ao Xu , Deqing Yang

Nowadays, formal theorem provers have made monumental progress on high-school and competition-level mathematics, but few of them generalize to more advanced mathematics. In this paper, we present REAL-Prover, a new open-source stepwise…

Computation and Language · Computer Science 2025-11-25 Ziju Shen , Naohao Huang , Fanyi Yang , Yutong Wang , Guoxiong Gao , Tianyi Xu , Jiedong Jiang , Wanyi He , Pu Yang , Mengzhou Sun , Haocheng Ju , Peihao Wu , Bryan Dai , Bin Dong

This paper introduces TurnaboutLLM, a novel framework and dataset for evaluating the deductive reasoning abilities of Large Language Models (LLMs) by leveraging the interactive gameplay of detective games Ace Attorney and Danganronpa. The…

Computation and Language · Computer Science 2025-09-23 Yuan Yuan , Muyu He , Muhammad Adil Shahid , Jiani Huang , Ziyang Li , Li Zhang

Check-worthiness detection is the task of identifying claims, worthy to be investigated by fact-checkers. Resource scarcity for non-world languages and model learning costs remain major challenges for the creation of models supporting…

Computation and Language · Computer Science 2023-01-16 Ipek Baris Schlicht , Lucie Flek , Paolo Rosso

This paper introduces several techniques that improve the scalability of the deductive verification of data-level programs working on arrays and matrices. First of all, we introduce a technique to rewrite expressions with (nested)…

Software Engineering · Computer Science 2026-05-14 Lars B. van den Haak , Anton Wijs , Marieke Huisman

Can agents be trained to answer difficult mathematical questions by playing a game? We consider the integer feasibility problem, a challenge of deciding whether a system of linear equations and inequalities has a solution with integer…

Machine Learning · Computer Science 2022-08-26 Yue Wu , Jesús A. De Loera

Some Transformer-based models can perform cross-lingual transfer learning: those models can be trained on a specific task in one language and give relatively good results on the same task in another language, despite having been pre-trained…

Computation and Language · Computer Science 2022-07-20 Félix Gaschi , François Plesse , Parisa Rastin , Yannick Toussaint

Answer verification identifies correct solutions among candidates generated by large language models (LLMs). Current approaches typically train verifier models by labeling solutions as correct or incorrect based solely on whether the final…

Computation and Language · Computer Science 2024-10-28 Akira Kawabata , Saku Sugawara

How does one measure "ability to understand language"? If it is a person's ability that is being measured, this is a question that almost never poses itself in an unqualified manner: Whatever formal test is applied, it takes place on the…

Computation and Language · Computer Science 2023-04-17 David Schlangen

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks, yet they still struggle to reliably verify the correctness of their own outputs. Existing solutions to this verification challenge often…

Computation and Language · Computer Science 2025-06-13 Yuhua Jiang , Yuwen Xiong , Yufeng Yuan , Chao Xin , Wenyuan Xu , Yu Yue , Qianchuan Zhao , Lin Yan

Deductive reasoning is the process of deriving conclusions strictly from the given premises, without relying on external knowledge. We define honesty in this setting as a model's ability to respond only when the conclusion is logically…

Computation and Language · Computer Science 2025-12-01 Jiarui Liu , Kaustubh Dhole , Yingheng Wang , Haoyang Wen , Sarah Zhang , Haitao Mao , Gaotang Li , Neeraj Varshney , Jingguo Liu , Xiaoman Pan

Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevailing paradigms typically rely on solitary rollout strategies where…

Computation and Language · Computer Science 2026-02-05 Lingzhuang Sun , Ruitong Liu , Yuxia Zhu , Xiaohan Xu , Jingxuan Wei , Xiangxiang Zhang , Bihui Yu , Wentao Zhang

Large Language Models (LLMs) have demonstrated strong generative capabilities but remain prone to inconsistencies and hallucinations. We introduce Peer Elicitation Games (PEG), a training-free, game-theoretic framework for aligning LLMs…

Machine Learning · Computer Science 2025-10-21 Baiting Chen , Tong Zhu , Jiale Han , Lexin Li , Gang Li , Xiaowu Dai

Recent advances in large language models (LLMs) have significantly enhanced automated legal reasoning. Yet, it remains unclear whether their performance reflects genuine legal reasoning ability or artifacts of data contamination. We present…

Artificial Intelligence · Computer Science 2026-05-18 Parisa Kordjamshidi , Samer Aslan , Madhavan Seshadri , Leslie Barrett , Enrico Santus

Most reinforcement learning (RL) methods for training large language models (LLMs) require ground-truth labels or task-specific verifiers, limiting scalability when correctness is ambiguous or expensive to obtain. We introduce Reinforcement…

Neural and Evolutionary Computing · Computer Science 2026-01-30 Micah Rentschler , Jesse Roberts

Real artificial intelligence always has been focused on by many machine learning researchers, especially in the area of deep learning. However deep neural network is hard to be understood and explained, and sometimes, even metaphysics. The…

Machine Learning · Computer Science 2019-10-22 Jinwei Zhao , Qizhou Wang , Fuqiang Zhang , Wanli Qiu , Yufei Wang , Yu Liu , Guo Xie , Weigang Ma , Bin Wang , Xinhong Hei

Developers often struggle to specify correct training labels and rewards. Perhaps they don't need to. We propose recontextualization, which reduces how often language models "game" training signals, performing misbehaviors those signals…

Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated critiques that pinpoint the errors. This work explores whether…

Computation and Language · Computer Science 2024-06-07 Yunxiang Zhang , Muhammad Khalifa , Lajanugen Logeswaran , Jaekyeom Kim , Moontae Lee , Honglak Lee , Lu Wang