English
Related papers

Related papers: ARBITER: Reasoning Trajectory Basins and Majority …

200 papers

Large Reasoning Models (LRMs) excel at complex reasoning tasks, but their efficiency is often hampered by overly verbose outputs. Prior steering methods attempt to address this issue by applying a single, global vector to hidden…

Machine Learning · Computer Science 2026-02-06 Yawei Li , Benjamin Bergner , Yinghan Zhao , Vihang Prakash Patil , Bei Chen , Cheng Wang

We study leveraging adaptive retrieval to ensure sufficient "bridge" documents are retrieved for reasoning-intensive retrieval. Bridge documents are those that contribute to the reasoning process yet are not directly relevant to the initial…

Information Retrieval · Computer Science 2026-04-15 Jongho Kim , Jaeyoung Kim , Seung-won Hwang , Jihyuk Kim , Yu Jin Kim , Moontae Lee

Recent advancements in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks. Current research enhances the reasoning performance of LLMs by sampling multiple…

Computation and Language · Computer Science 2024-05-22 Zhangyue Yin , Qiushi Sun , Qipeng Guo , Zhiyuan Zeng , Xiaonan Li , Tianxiang Sun , Cheng Chang , Qinyuan Cheng , Ding Wang , Xiaofeng Mou , Xipeng Qiu , XuanJing Huang

Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses. In this study, we investigate the underlying mechanisms behind the persistence of…

Computation and Language · Computer Science 2025-07-02 Daking Rai , Samuel Miller , Kevin Moran , Ziyu Yao

Speech recognition and other natural language tasks have long benefited from voting-based algorithms as a method to aggregate outputs from several systems to achieve a higher accuracy than any of the individual systems. Diarization, the…

Computation and Language · Computer Science 2020-02-06 Andreas Stolcke , Takuya Yoshioka

Scaling test-time compute by iteratively updating a latent state has emerged as a powerful paradigm for reasoning. Yet the internal mechanisms that enable these iterative models to generalize beyond memorized patterns remain unclear. We…

Machine Learning · Computer Science 2026-05-21 Benhao Huang , Zhengyang Geng , Zico Kolter

As language models regularly make mistakes when solving math problems, automated identification of errors in the reasoning process becomes increasingly significant for their scalable oversight. In this paper, we introduce ProcessBench for…

Artificial Intelligence · Computer Science 2025-05-27 Chujie Zheng , Zhenru Zhang , Beichen Zhang , Runji Lin , Keming Lu , Bowen Yu , Dayiheng Liu , Jingren Zhou , Junyang Lin

During deliberation processes, mediators and facilitators typically need to select a small and representative set of opinions later used to produce digestible reports for stakeholders. In online deliberation platforms, algorithmic selection…

Computers and Society · Computer Science 2026-02-18 Salim Hafid , Manon Berriche , Jean-Philippe Cointet

Recent advances in Large Reasoning Models (LRMs) have shown impressive capabilities in mathematical and logical reasoning. However, current LRMs rarely admit ignorance or respond with "I don't know". Instead, they often produce incorrect…

When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or completing agentic tasks, reasoning is implicit in almost all written text. For…

Computation and Language · Computer Science 2024-03-19 Eric Zelikman , Georges Harik , Yijia Shao , Varuna Jayasiri , Nick Haber , Noah D. Goodman

This paper introduces BI-Directional DEliberation Reasoning (BIDDER), a novel reasoning approach to enhance the decision rationality of language models. Traditional reasoning methods typically rely on historical information and employ…

Computation and Language · Computer Science 2024-07-09 Yadong Zhang , Shaoguang Mao , Wenshan Wu , Yan Xia , Tao Ge , Man Lan , Furu Wei

Chain-of-thought (CoT) reasoning and reasoning-tuned models such as DeepSeek-R1 are commonly assumed to reduce shallow heuristic biases by thinking carefully. We test this on position bias in multiple-choice QA and find a different story:…

Artificial Intelligence · Computer Science 2026-05-11 Xiao Wang

The theory of boosting provides a computational framework for aggregating approximate weak learning algorithms, which perform marginally better than a random predictor, into an accurate strong learner. In the realizable case, the success of…

Machine Learning · Computer Science 2024-11-01 Udaya Ghai , Karan Singh

Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…

Computation and Language · Computer Science 2026-05-11 Xuan Li , Yining Wang , Yuchen Liu , Guanjun Liu , Delai Qiu , Shengping Liu , Jiaen Liang , Wei Huang , Jun Yu , Junnan Zhu

Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-time scaling methods, such as repeated sampling, self-correction, and tree search,…

Artificial Intelligence · Computer Science 2026-04-30 Zhimin Lin , Yixin Ji , Jinpeng Li , Yu Luo , Dong Li , Junhua Fang , Juntao Li , Min Zhang

Automated Theorem Proving (ATP) deals with the development of computer programs being able to show that some conjectures (queries) are a logical consequence of a set of axioms (facts and rules). There exists several successful ATPs where…

Computation and Language · Computer Science 2021-09-20 Gabriele Picco , Hoang Thanh Lam , Marco Luca Sbodio , Vanessa Lopez Garcia

While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We introduce the Robust Reasoning Benchmark (RRB), a pipeline of…

Machine Learning · Computer Science 2026-05-22 Pavel Golikov , Evgenii Opryshko , Gennady Pekhimenko , Mark C. Jeffrey

Standard methods for aggregating natural language judgments, such as majority voting, often fail to produce logically consistent results when applied to high-conflict domains, treating differing opinions as noise. We propose a…

Computation and Language · Computer Science 2026-05-04 Sheza Munir , Ahanaf Rodoshi , Sumin Lee , Feiran Chang , Xujie Si , Syed Ishtiaque Ahmed

Ensuring the reliability of Large Language Models (LLMs) in complex reasoning tasks remains a formidable challenge, particularly in scenarios that demand precise mathematical calculations and knowledge-intensive open-domain generation. In…

Machine Learning · Computer Science 2025-05-27 Ali Razghandi , Seyed Mohammad Hadi Hosseini , Mahdieh Soleymani Baghshah

Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the…

Artificial Intelligence · Computer Science 2026-05-29 Yubo Li , Ramayya Krishnan , Rema Padman