Mitigating LLM Hallucinations via Conformal Abstention

• URL: http://arxiv.org/abs/2405.01563v1
• Date: Thu, 4 Apr 2024 11:32:03 GMT
• Title: Mitigating LLM Hallucinations via Conformal Abstention
• Authors: Yasin Abbasi Yadkori, Ilja Kuzborskij, David Stutz, András György, Adam Fisch, Arnaud Doucet, Iuliya Beloshapka, Wei-Hung Weng, Yao-Yuan Yang, Csaba Szepesvári, Ali Taylan Cemgil, Nenad Tomasev,
• Abstract summary: 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.
• Score: 70.83870602967625
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying "I don't know") in a general domain, instead of resorting to possibly "hallucinating" a non-sensical or incorrect answer. Building on earlier approaches that use self-consistency as a more reliable measure of model confidence, we propose using the LLM itself to self-evaluate the similarity between each of its sampled responses for a given query. We then further 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, while also maintaining a significantly less conservative abstention rate on a dataset with long responses (Temporal Sequences) compared to baselines using log-probability scores to quantify uncertainty, while achieveing comparable performance on a dataset with short answers (TriviaQA). To evaluate the experiments automatically, one needs to determine if two responses are equivalent given a question. Following standard practice, we use a thresholded similarity function to determine if two responses match, but also provide a method for calibrating the threshold based on conformal prediction, with theoretical guarantees on the accuracy of the match prediction, which might be of independent interest.

Related papers

• To Believe or Not to Believe Your LLM [51.2579827761899]
  We explore uncertainty quantification in large language models (LLMs) We derive an information-theoretic metric that allows to reliably detect when only epistemic uncertainty is large. We conduct a series of experiments which demonstrate the advantage of our formulation.
  arXiv  Detail & Related papers  (2024-06-04T17:58:18Z)
• Query Performance Prediction using Relevance Judgments Generated by Large Language Models [53.97064615557883]
  We propose a QPP framework using automatically generated relevance judgments (QPP-GenRE) QPP-GenRE decomposes QPP into independent subtasks of predicting relevance of each item in a ranked list to a given query. This allows us to predict any IR evaluation measure using the generated relevance judgments as pseudo-labels.
  arXiv  Detail & Related papers  (2024-04-01T09:33:05Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• Conformal Language Modeling [61.94417935386489]
  We propose a novel approach to conformal prediction for generative language models (LMs) Standard conformal prediction produces prediction sets with rigorous, statistical guarantees. We demonstrate the promise of our approach on multiple tasks in open-domain question answering, text summarization, and radiology report generation.
  arXiv  Detail & Related papers  (2023-06-16T21:55:08Z)
• Conformalized Unconditional Quantile Regression [27.528258690139793]
  We develop a predictive inference procedure that combines conformal prediction with unconditional quantile regression. We show that our procedure is adaptive to heteroscedasticity, provides transparent coverage guarantees that are relevant to the test instance at hand, and performs competitively with existing methods in terms of efficiency.
  arXiv  Detail & Related papers  (2023-04-04T00:20:26Z)
• Adaptive Conformal Prediction by Reweighting Nonconformity Score [0.0]
  We use a Quantile Regression Forest (QRF) to learn the distribution of nonconformity scores and utilize the QRF's weights to assign more importance to samples with residuals similar to the test point. Our approach enjoys an assumption-free finite sample marginal and training-conditional coverage, and under suitable assumptions, it also ensures conditional coverage.
  arXiv  Detail & Related papers  (2023-03-22T16:42:19Z)
• Data Association Aware POMDP Planning with Hypothesis Pruning Performance Guarantees [7.928094304325113]
  We introduce a pruning-based approach for planning with ambiguous data associations. Our key contribution is to derive bounds between the value function based on the complete set of hypotheses and the value function based on a pruned-subset of the hypotheses. We demonstrate how these bounds can both be used to certify any pruning in retrospect and propose a novel approach to determine which hypotheses to prune in order to ensure a predefined limit on the loss.
  arXiv  Detail & Related papers  (2023-03-03T18:35:01Z)
• Improving Adaptive Conformal Prediction Using Self-Supervised Learning [72.2614468437919]
  We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores. We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.
  arXiv  Detail & Related papers  (2023-02-23T18:57:14Z)
• Near-Optimal Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observations [44.71254888821376]
  We provide the first type-I-error and expected-rejection-time guarantees under general non-data generating processes. We show how to apply our results to inference on parameters defined by estimating equations, such as average treatment effects.
  arXiv  Detail & Related papers  (2022-12-29T18:37:08Z)
• Conformal Inference of Counterfactuals and Individual Treatment Effects [6.810856082577402]
  We propose a conformal inference-based approach that can produce reliable interval estimates for counterfactuals and individual treatment effects. Existing methods suffer from a significant coverage deficit even in simple models.
  arXiv  Detail & Related papers  (2020-06-11T01:03:32Z)

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.