Year: 2026
Type: conference-paper
Abstract: Chain-of-Thought (CoT) reasoning can enhance large language models (LLMs), but it requires manually designed prompts to guide the model.Recently proposed CoT-decoding enables the model to generate CoT-style reasoning paths without prompts, but it is only applicable to problems with fixed answer sets.To address this limitation, we propose a general decoding strategy-GCoT-decoding-that extends applicability to a broader range of question-answering tasks.GCoT-decoding employs a two-stage branching method combining Fibonacci sampling and heuristic error backtracking to generate candidate decoding paths.It then splits each path into a reasoning span and an answer span to accurately compute path confidence, and finally aggregates semantically similar paths to identify a consensus answer, replacing traditional majority voting.We conduct extensive experiments on six datasets covering both fixed and free QA tasks.Our method not only maintains strong performance on fixed QA but also achieves significant improvements on free QA, demonstrating its generality.
Institutions: Xiamen University, Minjiang University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166851742