Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
Self-consistency (SC), leveraging multiple samples from LLMs, shows significant gains on various reasoning tasks but struggles with free-form generation due to the difficulty of aggregating answers. Its variants, UCS and USC, rely on sample selection or voting mechanisms to improve output quality. These methods, however, face limitations due to their inability to fully utilize the nuanced consensus knowledge present within multiple candidate samples, often resulting in suboptimal outputs. We propose Fine-Grained Self-Consistency (FSC) to addresses these limitations by extracting and integrating segment-level commonalities from candidate samples, enhancing the performance of LLMs both in open-ended and reasoning tasks. Based on this, we present two additional strategies: candidate filtering, which enhances overall quality by identifying highly similar candidate sets, and merging, which reduces input token requirements by combining similar samples. The effectiveness of FSC is demonstrated through extensive experiments on various tasks, including summarization, code generation, and mathematical reasoning, using GPT-3.5-turbo and GPT-4. The results indicate significant improvements over baseline methods, showcasing the potential of FSC to optimize output quality by effectively synthesizing fine-grained consensus knowledge from multiple samples.
Code (1)
Tasks
Code GenerationFormMathematical ReasoningText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Take its Essence, Discard its Dross! Debiasing for Toxic Language Detection via Counterfactual Causal Effect
Current methods of toxic language detection (TLD) typically rely on specific tokens to conduct decisions, which makes them suffer from lexical bias, leading to inferior performance and generalization. Lexical bias has bo…
counterfactualCounterfactual InferenceFairnessSentenceNeuro-Symbolic Closed-Loop Control of Laser Powder Bed Fusion with an In-Loop Ontology
A geometry-conditioned, neuro-symbolic closed-loop architecture is proposed for laser powder bed fusion, in which a standards-aligned ontology operates inside the control loop and couples symbolic reasoning with statisti…
Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models
Data selection for fine-tuning Large Language Models (LLMs) aims to select a high-quality subset from a given candidate dataset to train a Pending Fine-tune Model (PFM) into a Selective-Enhanced Model (SEM). It can impro…
Learning logic programs by explaining their failures
Scientists form hypotheses and experimentally test them. If a hypothesis fails (is refuted), scientists try to explain the failure to eliminate other hypotheses. The more precise the failure analysis the more hypotheses …
Inductive logic programmingEliminating the Language Bias for Visual Question Answering with fine-grained Causal Intervention
Despite the remarkable advancements in Visual Question Answering (VQA), the challenge of mitigating the language bias introduced by textual information remains unresolved. Previous approaches capture language bias from a…
Contrastive LearningcounterfactualQuestion AnsweringSentence+2