ANCHOR constructs dense hierarchical factor spaces via LLM generation and clustering, then augments Naive Bayes with a causal Bayesian network to reduce unknown predictions and improve reliability of LLM-based probability estimates.
GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Chain-of-Thought reasoning can enhance large language models, 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.
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
unclear 1representative citing papers
FACT-E uses controlled perturbations as an instrumental signal to measure intra-chain faithfulness in CoT reasoning and combines it with answer consistency to select trustworthy trajectories.
citing papers explorer
-
ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models
ANCHOR constructs dense hierarchical factor spaces via LLM generation and clustering, then augments Naive Bayes with a causal Bayesian network to reduce unknown predictions and improve reliability of LLM-based probability estimates.
-
FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning
FACT-E uses controlled perturbations as an instrumental signal to measure intra-chain faithfulness in CoT reasoning and combines it with answer consistency to select trustworthy trajectories.