TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models
Enhancing the reasoning capability of large language models (LLMs) remains a core challenge in natural language processing. The Chain-of-Thought (CoT) paradigm dominates practical applications for its single-round efficiency, yet its reasoning chains often exhibit logical gaps. While multi-round paradigms like Graph-of-Thoughts (GoT), Tree-of-Thoughts (ToT), and Atom of Thought (AoT) achieve strong performance and reveal effective reasoning structures, their high cost limits practical use. To address this problem, this paper proposes a topology-based method for optimizing reasoning chains. The framework embeds essential topological patterns of effective reasoning into the lightweight CoT paradigm. Using persistent homology, we map CoT, ToT, and GoT into a unified topological space to quantify their structural features. On this basis, we design a unified optimization system: a Topological Optimization Agent diagnoses deviations in CoT chains from desirable topological characteristics and simultaneously generates targeted strategies to repair these structural deficiencies. Compared with multi-round reasoning methods like ToT and GoT, experiments on multiple datasets show that our approach offers a superior balance between reasoning accuracy and efficiency, showcasing a practical solution to ``single-round generation with multi-round intelligence''.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
GroupRAG: Cognitively Inspired Group-Aware Retrieval and Reasoning via Knowledge-Driven Problem Structuring
The performance of language models is commonly limited by insufficient knowledge and constrained reasoning. Prior approaches such as Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) address these issues by…
From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs
Large Language Models (LLMs), despite their success in question answering, exhibit limitations in complex multi-hop question answering (MQA) tasks that necessitate non-linear, structured reasoning. This limitation stems …
Multi-hop Question AnsweringKnowledge GraphsAligning Deep Implicit Preferences by Learning to Reason Defensively
Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit pref…
Reinforcement LearningKnowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning
Understanding complex biomolecular mechanisms requires multi-step reasoning across molecular interactions, signaling cascades, and metabolic pathways. While large language models(LLMs) show promise in such tasks, their a…
Reinforcement LearningQuestion AnsweringTRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant infor…
Question AnsweringRAGRetrievalRetrieval-augmented Generation