相关论文: ARBITER: Reasoning Trajectory Basins and Majority …

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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:…

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…

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…

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,…

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…

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…

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…

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…

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…