Confidence Improves Self-Consistency in LLMs (2025.findings-acl)

Copied to clipboard

Challenge: Modern large language models (LLMs) demonstrate strong reasoning capabilities, driven in part by their capacity to generate a sequence of intermediate reasoning steps that lead them toward a final answer.
Approach: They propose a method that performs a weighted majority vote based on confidence scores obtained directly from the model.
Outcome: The proposed method outperforms self-consistency on nine models and four datasets, reducing the required number of reasoning paths by over 40% on average.

Similar Papers

Self-Para-Consistency: Improving Reasoning Tasks at Low Cost for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Recent studies have shown that self-consistency decoding can improve performance for complex reasoning tasks with large language models.
Approach: They propose a self-consistency decoding strategy that generates multiple paraphrases for each test question and then generates reasoning paths for the original and all the paraphrased questions based on greedy decoding.
Outcome: The proposed strategy reduces the sampling number and improves performance on complex reasoning tasks.
VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection (2026.findings-acl)

Copied to clipboard

Challenge: Weighted majority voting requires a critic to evaluate each candidate’s reasoning trace to produce the answer’s confidence score.
Approach: They propose a lightweight framework that uses a measure of semantic similarity to filter reasoning traces that are semantically equivalent to others, degenerate, or hallucinated.
Outcome: The proposed framework reduces token usage by 47% while maintaining or exceeding the accuracy of CISC.
Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling (2025.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) generate reasoning paths before answers, but lack a systematic approach to determine optimal number of samples or select the most faithful rationale.
Approach: They propose a framework that evaluates the quality of reasoning and consistency of answers for each generated sample and uses criteria-based stopping and weighted majority voting to guide early stopping decisions and rationale selection.
Outcome: The proposed framework outperforms existing methods while maintaining accuracy.
Self-Training Large Language Models with Confident Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models generate reasoning paths before final answers, but learning such a path requires costly human supervision.
Approach: They propose a method that fine-tunes LLMs to prefer reasoning paths with high confidence . they propose 'cORE-PO' that fine tunes Lms to choose high-quality reasoning paths .
Outcome: The proposed method improves the accuracy of outputs on four in-distribution and two out-of-difference benchmarks.
Self-Consistency Boosts Calibration for Math Reasoning (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing solutions for math reasoning tasks use semantic parsing or AST decoding, but performance can degrade dramatically even with slight changes to the questions.
Approach: They propose three calibration methods based on self-consistency for math reasoning tasks.
Outcome: The proposed methods bridge model confidence and accuracy better than existing methods based on p(True) or logit.
Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to self-detection only retrospectively evaluate LLM-generated answers, leading to over-trust in incorrectly generated answers.
Approach: They propose a self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers to mitigate the over-trust in LLM generated incorrect answers.
Outcome: The proposed framework can be integrated with existing approaches for superior self-detection.
Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for improving the correctness of output from large language models generate a constant number of samples per question, but Adaptive-Consistency reduces sample budget by up to 7.9 times with an average accuracy drop of less than 0.1%.
Approach: They propose a model-agnostic technique that dynamically adjusts the number of samples per question using a lightweight stopping criterion.
Outcome: The proposed technique reduces sample budget by 7.9 times with an average accuracy drop of less than 0.1%.
Self-Ensemble: Mitigating Confidence Distortion for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models exhibit a confidence distortion problem on multichoice question-answering . Self-Ensemble solves this problem by splitting the choices into several groups .
Approach: They propose a method that splits LLM choices into several groups and ensembles them to reach a final decision.
Outcome: The proposed method outperforms standard inference and baseline methods on MCQA.
CER: Confidence Enhanced Reasoning in LLMs (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to enhance the reliability of Large Language Models (LLMs) in complex reasoning tasks are limited by their limitations.
Approach: They propose an uncertainty-aware framework to enhance the reliability of Large Language Models . they quantify the confidence of intermediate answers and evaluate the reliability based on these confidences a way that reflects the reliability.
Outcome: The proposed approach improves accuracy of large language models in math and open-domain tasks by 7.4% and 5.8% over baseline approaches.
Boosting Self-Consistency with Ranking (2026.acl-srw)

Copied to clipboard

Challenge: Existing approaches to improve performance of large language models include self-consistency, RISC, extended reasoning, and iterative self-correction.
Approach: They propose a test-time scaling technique that uses multiple features to score candidate answers in self-consistency as a ranking problem.
Outcome: The proposed method achieves better accuracy-efficiency trade-off than standard self-consistency and strong baselines on three datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations