FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation

• URL: http://arxiv.org/abs/2410.22257v1
• Date: Tue, 29 Oct 2024 17:19:56 GMT
• Title: FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation
• Authors: Farima Fatahi Bayat, Lechen Zhang, Sheza Munir, Lu Wang,
• Abstract summary: We present VERIFY, a pipeline to evaluate LMs' factuality in real-world user interactions. Verification considers the verifiability of LM-generated content and categorizes content units as supported, unsupported, or undecidable. We benchmark widely-used LMs from GPT, Gemini, and Llama3.1 family on FactBench.
• Score: 4.773086022844023
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models (LMs) are widely used by an increasing number of users, underscoring the challenge of maintaining factuality across a broad range of topics. We first present VERIFY (Verification and Evidence RetrIeval for FactualitY evaluation), a pipeline to evaluate LMs' factuality in real-world user interactions. VERIFY considers the verifiability of LM-generated content and categorizes content units as supported, unsupported, or undecidable based on the retrieved evidence from the Web. Importantly, factuality judgment by VERIFY correlates better with human evaluations than existing methods. Using VERIFY, we identify "hallucination prompts" across diverse topics, i.e., those eliciting the highest rates of incorrect and inconclusive LM responses. These prompts form FactBench, a dataset of 1K prompts across 150 fine-grained topics. Our dataset captures emerging factuality challenges in real-world LM interactions and can be regularly updated with new prompts. We benchmark widely-used LMs from GPT, Gemini, and Llama3.1 family on FactBench, yielding the following key findings: (i) Proprietary models exhibit better factuality, with performance declining from Easy to Hard hallucination prompts. (ii) Llama3.1-405B-Instruct shows comparable or lower factual accuracy than Llama3.1-70B-Instruct across all evaluation methods due to its higher subjectivity that leads to more content labeled as undecidable. (iii) Gemini1.5-Pro shows a significantly higher refusal rate, with over-refusal in 25% of cases. Our code and data are publicly available at https://huggingface.co/spaces/launch/factbench.

Related papers

• Verification with Transparency: The TrendFact Benchmark for Auditable Fact-Checking via Natural Language Explanation [10.449165630417522]
  We present TrendFact, the first Chinese fact-checking benchmark incorporating structured natural language explanations. TrendFact comprises 7,643 carefully curated samples from trending social media content and professional fact-checking repositories. It supports various forms of reasoning, including numerical, logical reasoning, and common sense verification.
  arXiv  Detail & Related papers  (2024-10-19T15:25:19Z)
• Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models [13.48296910438554]
  Hallucination issues persistently plagued current multimodal large language models (MLLMs) We introduce Reefknot, a benchmark specifically targeting relation hallucinations, consisting of over 20,000 samples derived from real-world scenarios. Our comparative evaluation across three distinct tasks revealed a substantial shortcoming in the capabilities of current MLLMs to mitigate relation hallucinations.
  arXiv  Detail & Related papers  (2024-08-18T10:07:02Z)
• Belief Revision: The Adaptability of Large Language Models Reasoning [63.0281286287648]
  We introduce Belief-R, a new dataset designed to test LMs' belief revision ability when presented with new evidence. Inspired by how humans suppress prior inferences, this task assesses LMs within the newly proposed delta reasoning framework. We evaluate $sim$30 LMs across diverse prompting strategies and found that LMs generally struggle to appropriately revise their beliefs in response to new information.
  arXiv  Detail & Related papers  (2024-06-28T09:09:36Z)
• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction [85.26780391682894]
  We propose Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction (FENICE) FENICE leverages an NLI-based alignment between information in the source document and a set of atomic facts, referred to as claims, extracted from the summary. Our metric sets a new state of the art on AGGREFACT, the de-facto benchmark for factuality evaluation.
  arXiv  Detail & Related papers  (2024-03-04T17:57:18Z)
• AttributionBench: How Hard is Automatic Attribution Evaluation? [19.872081697282002]
  We present AttributionBench, a comprehensive benchmark compiled from various existing attribution datasets. Our experiments show that even a fine-tuned GPT-3.5 only achieves around 80% macro-F1 under a binary classification formulation. A detailed analysis of more than 300 error cases indicates that a majority of failures stem from the model's inability to process nuanced information.
  arXiv  Detail & Related papers  (2024-02-23T04:23:33Z)
• TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization [29.49641083851667]
  We propose a new evaluation benchmark on topic-focused dialogue summarization, generated by LLMs of varying sizes. We provide binary sentence-level human annotations of the factual consistency of these summaries along with detailed explanations of factually inconsistent sentences.
  arXiv  Detail & Related papers  (2024-02-20T18:58:49Z)
• FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
  FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs. FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation. We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
  arXiv  Detail & Related papers  (2023-10-18T16:27:49Z)
• FELM: Benchmarking Factuality Evaluation of Large Language Models [40.78878196872095]
  We introduce a benchmark for Factuality Evaluation of large Language Models, referred to as felm. We collect responses generated from large language models and annotate factuality labels in a fine-grained manner. Our findings reveal that while retrieval aids factuality evaluation, current LLMs are far from satisfactory to faithfully detect factual errors.
  arXiv  Detail & Related papers  (2023-10-01T17:37:31Z)
• Generating Benchmarks for Factuality Evaluation of Language Models [61.69950787311278]
  We propose FACTOR: Factual Assessment via Corpus TransfORmation, a scalable approach for evaluating LM factuality. FACTOR automatically transforms a factual corpus of interest into a benchmark evaluating an LM's propensity to generate true facts from the corpus vs. similar but incorrect statements. We show that: (i) our benchmark scores increase with model size and improve when the LM is augmented with retrieval; (ii) benchmark score and perplexity do not always agree on model ranking; (iii) when perplexity and benchmark score disagree, the latter better reflects factuality in open-ended generation.
  arXiv  Detail & Related papers  (2023-07-13T17:14:38Z)
• Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy [68.31760483418901]
  Large Language Models(LLMs) struggle with providing current information due to the outdated pre-training data. Existing methods for updating LLMs, such as knowledge editing and continual fine-tuning, have significant drawbacks in generalizability of new information. We identify the core challenge behind these drawbacks: the LM-logical discrepancy featuring the difference between language modeling probabilities and logical probabilities.
  arXiv  Detail & Related papers  (2023-05-29T19:48:37Z)
• SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models [55.60306377044225]
  "SelfCheckGPT" is a simple sampling-based approach to fact-check the responses of black-box models. We investigate this approach by using GPT-3 to generate passages about individuals from the WikiBio dataset.
  arXiv  Detail & Related papers  (2023-03-15T19:31:21Z)
• WiCE: Real-World Entailment for Claims in Wikipedia [63.234352061821625]
  We propose WiCE, a new fine-grained textual entailment dataset built on natural claim and evidence pairs extracted from Wikipedia. In addition to standard claim-level entailment, WiCE provides entailment judgments over sub-sentence units of the claim. We show that real claims in our dataset involve challenging verification and retrieval problems that existing models fail to address.
  arXiv  Detail & Related papers  (2023-03-02T17:45:32Z)

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.