FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees

• URL: http://arxiv.org/abs/2411.02603v3
• Date: Thu, 07 Nov 2024 03:17:42 GMT
• Title: FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees
• Authors: Fan Nie, Xiaotian Hou, Shuhang Lin, James Zou, Huaxiu Yao, Linjun Zhang,
• Abstract summary: Large Language Models (LLMs) to generate hallucinations and non-factual content undermines their reliability in high-stakes domains. We introduce FactTest, a novel framework that statistically assesses whether a LLM can confidently provide correct answers to given questions. We show that FactTest effectively detects hallucinations and improves the model's ability to abstain from answering unknown questions, leading to an over 40% accuracy improvement.
• Score: 41.78390564658645
• License:
• Abstract: The propensity of Large Language Models (LLMs) to generate hallucinations and non-factual content undermines their reliability in high-stakes domains, where rigorous control over Type I errors (the conditional probability of incorrectly classifying hallucinations as truthful content) is essential. Despite its importance, formal verification of LLM factuality with such guarantees remains largely unexplored. In this paper, we introduce FactTest, a novel framework that statistically assesses whether a LLM can confidently provide correct answers to given questions with high-probability correctness guarantees. We formulate factuality testing as hypothesis testing problem to enforce an upper bound of Type I errors at user-specified significance levels. Notably, we prove that our framework also ensures strong Type II error control under mild conditions and can be extended to maintain its effectiveness when covariate shifts exist. Our approach is distribution-free and works for any number of human-annotated samples. It is model-agnostic and applies to any black-box or white-box LM. Extensive experiments on question-answering (QA) and multiple-choice benchmarks demonstrate that FactTest effectively detects hallucinations and improves the model's ability to abstain from answering unknown questions, leading to an over 40% accuracy improvement.

Related papers

• Credal Two-Sample Tests of Epistemic Ignorance [34.42566984003255]
  We introduce credal two-sample testing, a new hypothesis testing framework for comparing credal sets. We generalise two-sample tests to compare credal sets, enabling reasoning for equality, inclusion, intersection, and mutual exclusivity.
  arXiv  Detail & Related papers  (2024-10-16T18:09:09Z)
• 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)
• Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification [116.77055746066375]
  Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. We propose a novel fact-checking and hallucination detection pipeline based on token-level uncertainty quantification.
  arXiv  Detail & Related papers  (2024-03-07T17:44:17Z)
• Distinguishing the Knowable from the Unknowable with Language Models [15.471748481627143]
  In the absence of ground-truth probabilities, we explore a setting where, in order to disentangle a given uncertainty, a significantly larger model stands in as a proxy for the ground truth. We show that small linear probes trained on the embeddings of frozen, pretrained models accurately predict when larger models will be more confident at the token level. We propose a fully unsupervised method that achieves non-trivial accuracy on the same task.
  arXiv  Detail & Related papers  (2024-02-05T22:22:49Z)
• Max-Rank: Efficient Multiple Testing for Conformal Prediction [43.56898111853698]
  Multiple hypothesis testing (MHT) commonly arises in various scientific fields, from genomics to psychology, where testing many hypotheses simultaneously increases the risk of Type-I errors. We propose a novel correction named $textttmax-rank$ that leverages these dependencies, whilst ensuring that the joint Type-I error rate is efficiently controlled.
  arXiv  Detail & Related papers  (2023-11-17T22:44:22Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Deep anytime-valid hypothesis testing [29.273915933729057]
  We propose a general framework for constructing powerful, sequential hypothesis tests for nonparametric testing problems. We develop a principled approach of leveraging the representation capability of machine learning models within the testing-by-betting framework. Empirical results on synthetic and real-world datasets demonstrate that tests instantiated using our general framework are competitive against specialized baselines.
  arXiv  Detail & Related papers  (2023-10-30T09:46:19Z)
• Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning [76.98542249776257]
  Large-scale language models often face the challenge of "hallucination" We introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
  arXiv  Detail & Related papers  (2023-10-07T12:06:53Z)
• Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback [91.22679548111127]
  A trustworthy real-world prediction system should produce well-calibrated confidence scores. We show that verbalized confidences emitted as output tokens are typically better-calibrated than the model's conditional probabilities.
  arXiv  Detail & Related papers  (2023-05-24T10:12:33Z)
• Testing for Overfitting [0.0]
  We discuss the overfitting problem and explain why standard and concentration results do not hold for evaluation with training data. We introduce and argue for a hypothesis test by means of which both model performance may be evaluated using training data.
  arXiv  Detail & Related papers  (2023-05-09T22:49:55Z)

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.