Large language model validity via enhanced conformal prediction methods

• URL: http://arxiv.org/abs/2406.09714v2
• Date: Thu, 31 Oct 2024 05:31:03 GMT
• Title: Large language model validity via enhanced conformal prediction methods
• Abstract summary: We develop new conformal inference methods for obtaining validity guarantees on the output of large language models (LLMs) We generalize the conditional conformal procedure of Gibbs et al. (2023) in order to adaptively issue weaker guarantees when they are required to preserve the utility of the output. We demonstrate the efficacy of our approach on biography and medical question-answering datasets.
• Score: 4.081098869497239
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We develop new conformal inference methods for obtaining validity guarantees on the output of large language models (LLMs). Prior work in conformal language modeling identifies a subset of the text that satisfies a high-probability guarantee of correctness. These methods work by filtering claims from the LLM's original response if a scoring function evaluated on the claim fails to exceed a threshold calibrated via split conformal prediction. Existing methods in this area suffer from two deficiencies. First, the guarantee stated is not conditionally valid. The trustworthiness of the filtering step may vary based on the topic of the response. Second, because the scoring function is imperfect, the filtering step can remove many valuable and accurate claims. We address both of these challenges via two new conformal methods. First, we generalize the conditional conformal procedure of Gibbs et al. (2023) in order to adaptively issue weaker guarantees when they are required to preserve the utility of the output. Second, we show how to systematically improve the quality of the scoring function via a novel algorithm for differentiating through the conditional conformal procedure. We demonstrate the efficacy of our approach on biography and medical question-answering datasets.

Related papers

• Simultaneous Coverage and Efficiency Guarantee in Online Conformal Prediction [5.533296779866529]
  Adaptive conformal inference (ACI) of Gibbs and Cands and its variants are the standard approach to online conformal prediction under distribution shift.<n>Existing guarantees say nothing about prediction-set size, so validity can be achieved trivially at the cost of unduly wide prediction sets.<n>We consider a unified online learning framework that simultaneously controls absolute, non-optimal coverage violation and prediction-set efficiency.
  arXiv  Detail & Related papers  (2026-07-29T07:56:59Z)
• Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models [86.8650252164764]
  Large language models (LLMs) are prone to generating factually incorrect outputs.<n>We propose an adaptive conformal prediction approach that extends conformal score transformation methods to LLMs.<n>This enables prompt-dependent calibration, retaining marginal coverage guarantees while improving conditional coverage.
  arXiv  Detail & Related papers  (2026-04-15T15:35:42Z)
• LEC: Linear Expectation Constraints for False-Discovery Control in Selective Prediction and Routing Systems [95.35293543918762]
  Large language models (LLMs) often generate unreliable answers, while uncertainty methods fail to fully distinguish correct from incorrect predictions.<n>We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed a target risk level.<n>We propose LEC, which reinterprets selective prediction as a constrained decision problem by enforcing a Linear Expectation Constraint.
  arXiv  Detail & Related papers  (2025-12-01T11:27:09Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling [90.86991492288487]
  evaluating constraint on every token can be prohibitively expensive. LCD can distort the global distribution over strings, sampling tokens based only on local information. We show that our approach is superior to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-04-07T18:30:18Z)
• Conformal Linguistic Calibration: Trading-off between Factuality and Specificity [41.45862052156885]
  We propose a unified framework that connects abstention and linguistic calibration through the lens of linguistic pragmatics. We describe an implementation that allows for controlling the level of imprecision in model responses. Our approach enables fine-tuning models to perform uncertainty-aware adaptive claim rewriting, offering a controllable balance between factuality and specificity.
  arXiv  Detail & Related papers  (2025-02-26T13:01:49Z)
• Rectifying Conformity Scores for Better Conditional Coverage [75.73184036344908]
  We present a new method for generating confidence sets within the split conformal prediction framework. Our method performs a trainable transformation of any given conformity score to improve conditional coverage while ensuring exact marginal coverage.
  arXiv  Detail & Related papers  (2025-02-22T19:54:14Z)
• Assessing Correctness in LLM-Based Code Generation via Uncertainty Estimation [0.0]
  We explore uncertainty estimation as a proxy for correctness in LLM-generated code. We adapt two state-of-the-art techniques from natural language generation to the domain of code generation. Our findings indicate a strong correlation between the uncertainty computed through these techniques and correctness.
  arXiv  Detail & Related papers  (2025-02-17T10:03:01Z)
• Localizing Factual Inconsistencies in Attributable Text Generation [91.981439746404]
  We introduce QASemConsistency, a new formalism for localizing factual inconsistencies in attributable text generation. We first demonstrate the effectiveness of the QASemConsistency methodology for human annotation. We then implement several methods for automatically detecting localized factual inconsistencies.
  arXiv  Detail & Related papers  (2024-10-09T22:53:48Z)
• Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering [55.15192437680943]
  Generative models lack rigorous statistical guarantees for their outputs. We propose a sequential conformal prediction method producing prediction sets that satisfy a rigorous statistical guarantee. This guarantee states that with high probability, the prediction sets contain at least one admissible (or valid) example.
  arXiv  Detail & Related papers  (2024-10-02T15:26:52Z)
• Adjusting Regression Models for Conditional Uncertainty Calibration [46.69079637538012]
  We propose a novel algorithm to train a regression function to improve the conditional coverage after applying the split conformal prediction procedure. We establish an upper bound for the miscoverage gap between the conditional coverage and the nominal coverage rate and propose an end-to-end algorithm to control this upper bound.
  arXiv  Detail & Related papers  (2024-09-26T01:55:45Z)
• Length Optimization in Conformal Prediction [22.733758606168873]
  We develop Conformal Prediction with Length-Optimization (CPL) as a principled framework for conformal prediction. CPL constructs prediction sets with (near-) optimal length while ensuring conditional validity. Our empirical evaluations demonstrate the superior prediction set size performance of CPL compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-06-27T01:08:04Z)
• Mitigating LLM Hallucinations via Conformal Abstention [70.83870602967625]
  We develop a principled procedure for determining when a large language model should abstain from responding in a general domain. We leverage conformal prediction techniques to develop an abstention procedure that benefits from rigorous theoretical guarantees on the hallucination rate (error rate) Experimentally, our resulting conformal abstention method reliably bounds the hallucination rate on various closed-book, open-domain generative question answering datasets.
  arXiv  Detail & Related papers  (2024-04-04T11:32:03Z)
• 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)
• Split Localized Conformal Prediction [20.44976410408424]
  We propose a modified non-conformity score by leveraging local approximation of the conditional distribution. The modified score inherits the spirit of split conformal methods, which is simple and efficient compared with full conformal methods.
  arXiv  Detail & Related papers  (2022-06-27T07:53:38Z)
• Practical Adversarial Multivalid Conformal Prediction [27.179891682629183]
  We give a generic conformal prediction method for sequential prediction. It achieves target empirical coverage guarantees against adversarially chosen data. It is computationally lightweight -- comparable to split conformal prediction.
  arXiv  Detail & Related papers  (2022-06-02T14:33:00Z)
• Efficient and Differentiable Conformal Prediction with General Function Classes [96.74055810115456]
  We propose a generalization of conformal prediction to multiple learnable parameters. We show that it achieves approximate valid population coverage and near-optimal efficiency within class. Experiments show that our algorithm is able to learn valid prediction sets and improve the efficiency significantly.
  arXiv  Detail & Related papers  (2022-02-22T18:37:23Z)
• Part-X: A Family of Stochastic Algorithms for Search-Based Test Generation with Probabilistic Guarantees [3.9119084077397863]
  falsification has proven to be a practical and effective method for discovering erroneous behaviors in Cyber-Physical Systems. Despite the constant improvements on the performance and applicability of falsification methods, they all share a common characteristic. They are best-effort methods which do not provide any guarantees on the absence of erroneous behaviors (falsifiers) when the testing budget is exhausted.
  arXiv  Detail & Related papers  (2021-10-20T19:05:00Z)
• Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
  Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
  arXiv  Detail & Related papers  (2020-04-29T10:54:40Z)

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.