TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization

• URL: http://arxiv.org/abs/2402.13249v2
• Date: Sun, 31 Mar 2024 15:30:34 GMT
• Title: TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization
• Authors: Liyan Tang, Igor Shalyminov, Amy Wing-mei Wong, Jon Burnsky, Jake W. Vincent, Yu'an Yang, Siffi Singh, Song Feng, Hwanjun Song, Hang Su, Lijia Sun, Yi Zhang, Saab Mansour, Kathleen McKeown,
• Abstract summary: 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.
• Score: 29.49641083851667
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Single document news summarization has seen substantial progress on faithfulness in recent years, driven by research on the evaluation of factual consistency, or hallucinations. We ask whether these advances carry over to other text summarization domains. 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. Our analysis shows that existing LLMs hallucinate significant amounts of factual errors in the dialogue domain, regardless of the model's size. On the other hand, when LLMs, including GPT-4, serve as binary factual evaluators, they perform poorly and can be outperformed by prevailing state-of-the-art specialized factuality evaluation metrics. Finally, we conducted an analysis of hallucination types with a curated error taxonomy. We find that there are diverse errors and error distributions in model-generated summaries and that non-LLM based metrics can capture all error types better than LLM-based evaluators.

Related papers

• Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogism [62.571419297164645]
  This paper provides a systematic overview of prior works on the logical reasoning ability of large language models for analyzing categorical syllogisms. We first investigate all the possible variations for the categorical syllogisms from a purely logical perspective. We then examine the underlying configurations (i.e., mood and figure) tested by the existing datasets.
  arXiv  Detail & Related papers  (2024-06-26T21:17:20Z)
• Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends [38.86240794422485]
  We evaluate the faithfulness of large language models for dialogue summarization. Our evaluation reveals subtleties as to what constitutes a hallucination. We introduce two prompt-based approaches for fine-grained error detection that outperform existing metrics.
  arXiv  Detail & Related papers  (2024-06-05T17:49:47Z)
• Decompose and Aggregate: A Step-by-Step Interpretable Evaluation Framework [75.81096662788254]
  Large Language Models (LLMs) are scalable and economical evaluators. The question of how reliable these evaluators are has emerged as a crucial research question. We propose Decompose and Aggregate, which breaks down the evaluation process into different stages based on pedagogical practices.
  arXiv  Detail & Related papers  (2024-05-24T08:12:30Z)
• VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models [57.43276586087863]
  Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the models generate plausible-sounding but factually incorrect outputs. Existing benchmarks are often limited in scope, focusing mainly on object hallucinations. We introduce a multi-dimensional benchmark covering objects, attributes, and relations, with challenging images selected based on associative biases.
  arXiv  Detail & Related papers  (2024-04-22T04:49:22Z)
• 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)
• Exploring the Factual Consistency in Dialogue Comprehension of Large Language Models [51.75805497456226]
  This work focuses on the factual consistency issue with the help of the dialogue summarization task. Our evaluation shows that, on average, 26.8% of the summaries generated by LLMs contain factual inconsistency. To stimulate and enhance the dialogue comprehension ability of LLMs, we propose a fine-tuning paradigm with auto-constructed multi-task data.
  arXiv  Detail & Related papers  (2023-11-13T09:32:12Z)
• Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs [8.526956860672698]
  Large Language Models (LLMs) have gained immense attention due to their notable emergent capabilities. This study investigates the potential of LLMs as reliable assessors of factual consistency in summaries generated by text-generation models.
  arXiv  Detail & Related papers  (2023-11-01T17:42:45Z)
• 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)
• Summarization is (Almost) Dead [49.360752383801305]
  We develop new datasets and conduct human evaluation experiments to evaluate the zero-shot generation capability of large language models (LLMs) Our findings indicate a clear preference among human evaluators for LLM-generated summaries over human-written summaries and summaries generated by fine-tuned models.
  arXiv  Detail & Related papers  (2023-09-18T08:13:01Z)
• Evaluating Factual Consistency of Summaries with Large Language Models [24.416837319515896]
  We explore evaluating factual consistency of summaries by directly prompting large language models (LLMs) Our experiments demonstrate that prompting LLMs is able to outperform the previous best factuality systems in all settings.
  arXiv  Detail & Related papers  (2023-05-23T13:48:32Z)

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.