Multicalibration for Confidence Scoring in LLMs

• URL: http://arxiv.org/abs/2404.04689v1
• Date: Sat, 6 Apr 2024 17:33:37 GMT
• Title: Multicalibration for Confidence Scoring in LLMs
• Authors: Gianluca Detommaso, Martin Bertran, Riccardo Fogliato, Aaron Roth,
• Abstract summary: This paper proposes the use of "multicalibration" to yield interpretable and reliable confidence scores for outputs generated by large language models (LLMs) We show how to form groupings for prompt/completion pairs that are correlated with the probability of correctness via two techniques: clustering within an embedding space, and "self-annotation" We show how our techniques can yield confidence scores that provide substantial improvements in fine-grained measures of both calibration and accuracy compared to existing methods.
• Score: 6.948522445499497
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper proposes the use of "multicalibration" to yield interpretable and reliable confidence scores for outputs generated by large language models (LLMs). Multicalibration asks for calibration not just marginally, but simultaneously across various intersecting groupings of the data. We show how to form groupings for prompt/completion pairs that are correlated with the probability of correctness via two techniques: clustering within an embedding space, and "self-annotation" - querying the LLM by asking it various yes-or-no questions about the prompt. We also develop novel variants of multicalibration algorithms that offer performance improvements by reducing their tendency to overfit. Through systematic benchmarking across various question answering datasets and LLMs, we show how our techniques can yield confidence scores that provide substantial improvements in fine-grained measures of both calibration and accuracy compared to existing methods.

Related papers

• Diversified Sampling Improves Scaling LLM inference [31.18762591875725]
  DivSampling is a novel and versatile sampling technique designed to enhance the diversity of candidate solutions. Our theoretical analysis demonstrates that, under mild assumptions, the error rates of responses generated from diverse prompts are significantly lower compared to those produced by stationary prompts.
  arXiv  Detail & Related papers  (2025-02-16T07:37:58Z)
• Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles [4.477423478591491]
  Calib-n is a novel framework that trains an auxiliary model for confidence estimation. We find that few-shot prompts are the most effective for auxiliary model-based methods.
  arXiv  Detail & Related papers  (2025-01-07T18:48:42Z)
• Graph-based Confidence Calibration for Large Language Models [22.394717844099684]
  We propose a novel method to develop a well-calibrated confidence estimation model. We use a weighted graph to represent the consistency among the large language models' responses to a question. We then train a graph neural network to estimate the probability of correct responses.
  arXiv  Detail & Related papers  (2024-11-03T20:36:44Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• Dynamic Correlation Learning and Regularization for Multi-Label Confidence Calibration [60.95748658638956]
  This paper introduces the Multi-Label Confidence task, aiming to provide well-calibrated confidence scores in multi-label scenarios. Existing single-label calibration methods fail to account for category correlations, which are crucial for addressing semantic confusion. We propose the Dynamic Correlation Learning and Regularization algorithm, which leverages multi-grained semantic correlations to better model semantic confusion.
  arXiv  Detail & Related papers  (2024-07-09T13:26:21Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Calibrating Large Language Models with Sample Consistency [76.23956851098598]
  We explore the potential of deriving confidence from the distribution of multiple randomly sampled model generations, via three measures of consistency. Results show that consistency-based calibration methods outperform existing post-hoc approaches. We offer practical guidance on choosing suitable consistency metrics for calibration, tailored to the characteristics of various LMs.
  arXiv  Detail & Related papers  (2024-02-21T16:15:20Z)
• Calibrating Long-form Generations from Large Language Models [34.72041258464477]
  Large Language Models' (LLMs) confidence scores should align with the actual likelihood of its responses being correct. Current confidence elicitation methods and calibration metrics rely on a binary true/false assessment of response correctness. We introduce a unified calibration framework, in which both the correctness of the LLMs' responses and their associated confidence levels are treated as distributions across a range of scores.
  arXiv  Detail & Related papers  (2024-02-09T17:00:32Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.