Reasoning Court: Combining Reasoning, Action, and Judgment for Multi-Hop Reasoning

• URL: http://arxiv.org/abs/2504.09781v1
• Date: Mon, 14 Apr 2025 00:56:08 GMT
• Title: Reasoning Court: Combining Reasoning, Action, and Judgment for Multi-Hop Reasoning
• Authors: Jingtian Wu, Claire Cardie,
• Abstract summary: Reasoning Court (RC) is a novel framework that extends iterative reasoning-and-retrieval methods, such as ReAct, with a dedicated LLM judge.<n>RC consistently outperforms state-of-the-art few-shot prompting methods without task-specific fine-tuning.
• Score: 17.829990749622496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large language models (LLMs) have demonstrated strong capabilities in tasks like question answering and fact verification, they continue to suffer from hallucinations and reasoning errors, especially in multi-hop tasks that require integration of multiple information sources. Current methods address these issues through retrieval-based techniques (grounding reasoning in external evidence), reasoning-based approaches (enhancing coherence via improved prompting), or hybrid strategies combining both elements. One prominent hybrid method, ReAct, has outperformed purely retrieval-based or reasoning-based approaches; however, it lacks internal verification of intermediate reasoning steps, allowing potential errors to propagate through complex reasoning tasks. In this paper, we introduce Reasoning Court (RC), a novel framework that extends iterative reasoning-and-retrieval methods, such as ReAct, with a dedicated LLM judge. Unlike ReAct, RC employs this judge to independently evaluate multiple candidate answers and their associated reasoning generated by separate LLM agents. The judge is asked to select the answer that it considers the most factually grounded and logically coherent based on the presented reasoning and evidence, or synthesizes a new answer using available evidence and its pre-trained knowledge if all candidates are inadequate, flawed, or invalid. Evaluations on multi-hop benchmarks (HotpotQA, MuSiQue) and fact-verification (FEVER) demonstrate that RC consistently outperforms state-of-the-art few-shot prompting methods without task-specific fine-tuning.

Related papers

• Short-Path Prompting in LLMs: Analyzing Reasoning Instability and Solutions for Robust Performance [33.16322104912836]
  Large language models' (LLMs) reasoning is largely due to the chain-of-thought (CoT) approaches. LLMs are instruction-tuned to provide long and detailed CoT pathways when responding to reasoning-related questions. Human beings are naturally cognitive misers and will prompt language models to give rather short responses.
  arXiv  Detail & Related papers  (2025-04-13T14:12:14Z)
• Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning [19.477062052536887]
  We propose the Logical-Semantic Integration Model (LSIM), a supervised framework that bridges semantic and logical coherence.<n>LSIM comprises three components: reinforcement learning predicts a structured fact-rule chain for each question, a trainable Deep Structured Semantic Model (DSSM) retrieves the most relevant candidate questions and in-answer learning generates the final answer.<n>Our experiments on a real-world legal dataset QA-validated through both automated metrics and human evaluation-demonstrate that LSIM significantly enhances accuracy and reliability compared to existing methods.
  arXiv  Detail & Related papers  (2025-02-11T19:33:07Z)
• JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking [81.88787401178378]
  We introduce JudgeRank, a novel agentic reranker that emulates human cognitive processes when assessing document relevance. We evaluate JudgeRank on the reasoning-intensive BRIGHT benchmark, demonstrating substantial performance improvements over first-stage retrieval methods. In addition, JudgeRank performs on par with fine-tuned state-of-the-art rerankers on the popular BEIR benchmark, validating its zero-shot generalization capability.
  arXiv  Detail & Related papers  (2024-10-31T18:43:12Z)
• Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning [52.83539473110143]
  We introduce a novel structure-oriented analysis method to help Large Language Models (LLMs) better understand a question. To further improve the reliability in complex question-answering tasks, we propose a multi-agent reasoning system, Structure-oriented Autonomous Reasoning Agents (SARA) Extensive experiments verify the effectiveness of the proposed reasoning system. Surprisingly, in some cases, the system even surpasses few-shot methods.
  arXiv  Detail & Related papers  (2024-10-18T05:30:33Z)
• Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models [84.15513004135576]
  Current research enhances the reasoning performance of Large Language Models (LLMs) by sampling multiple reasoning chains and ensembling based on the answer frequency. This approach fails in scenarios where the correct answers are in the minority. We introduce a hierarchical reasoning aggregation framework AoR, which selects answers based on the evaluation of reasoning chains.
  arXiv  Detail & Related papers  (2024-05-21T17:12:19Z)
• Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning [74.90592233107712]
  We propose a Direct-Indirect Reasoning (DIR) method, which considers Direct Reasoning (DR) and Indirect Reasoning (IR) as multiple parallel reasoning paths that are merged to derive the final answer.<n>Our DIR method is simple yet effective and can be straightforwardly integrated with existing variants of CoT methods.
  arXiv  Detail & Related papers  (2024-02-06T03:41:12Z)
• LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning [61.7853049843921]
  Chain-of-thought (CoT) prompting is a popular in-context learning approach for large language models (LLMs) This paper introduces a new approach named Latent Reasoning Skills (LaRS) that employs unsupervised learning to create a latent space representation of rationales.
  arXiv  Detail & Related papers  (2023-12-07T20:36:10Z)
• Concise and Organized Perception Facilitates Reasoning in Large Language Models [31.238220405009617]
  Exploiting large language models (LLMs) to tackle reasoning has garnered growing attention.<n>It still remains highly challenging to achieve satisfactory results in complex logical problems, characterized by plenty of premises within the context and requiring multi-hop reasoning.<n>In this work, we first examine the mechanism from the perspective of information flow and reveal that LLMs confront difficulties akin to human-like cognitive biases when dealing with disordered and irrelevant content in reasoning tasks.
  arXiv  Detail & Related papers  (2023-10-05T04:47:49Z)
• HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision [118.0818807474809]
  This work proposes a principled, probabilistic approach for training explainable multi-hop QA systems without rationale supervision. Our approach performs multi-hop reasoning by explicitly modeling rationales as sets, enabling the model to capture interactions between documents and sentences within a document.
  arXiv  Detail & Related papers  (2023-05-23T16:53:49Z)
• ReAct: Synergizing Reasoning and Acting in Language Models [44.746116256516046]
  We show that large language models (LLMs) can generate both reasoning traces and task-specific actions in an interleaved manner. We apply our approach, named ReAct, to a diverse set of language and decision making tasks. ReAct overcomes issues of hallucination and error propagation prevalent in chain-of-thought reasoning by interacting with a simple Wikipedia API.
  arXiv  Detail & Related papers  (2022-10-06T01:00:32Z)
• EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension [39.970232108247394]
  Reasoning machine reading comprehension (R-MRC) aims to answer complex questions that require discrete reasoning based on text. Previous end-to-end methods that achieve state-of-the-art performance rarely solve the problem by paying enough emphasis on the modeling of evidence. We propose an evidence-emphasized discrete reasoning approach (EviDR), in which sentence and clause level evidence is first detected based on distant supervision.
  arXiv  Detail & Related papers  (2021-08-18T06:49:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.