Long-Form Information Alignment Evaluation Beyond Atomic Facts

• URL: http://arxiv.org/abs/2505.15792v1
• Date: Wed, 21 May 2025 17:46:38 GMT
• Title: Long-Form Information Alignment Evaluation Beyond Atomic Facts
• Authors: Danna Zheng, Mirella Lapata, Jeff Z. Pan,
• Abstract summary: We introduce MontageLie, a benchmark that constructs deceptive narratives by "montaging" truthful statements without introducing explicit hallucinations.<n>We propose DoveScore, a novel framework that jointly verifies factual accuracy and event-order consistency.
• Score: 60.25969380388974
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Information alignment evaluators are vital for various NLG evaluation tasks and trustworthy LLM deployment, reducing hallucinations and enhancing user trust. Current fine-grained methods, like FactScore, verify facts individually but neglect inter-fact dependencies, enabling subtle vulnerabilities. In this work, we introduce MontageLie, a challenging benchmark that constructs deceptive narratives by "montaging" truthful statements without introducing explicit hallucinations. We demonstrate that both coarse-grained LLM-based evaluators and current fine-grained frameworks are susceptible to this attack, with AUC-ROC scores falling below 65%. To enable more robust fine-grained evaluation, we propose DoveScore, a novel framework that jointly verifies factual accuracy and event-order consistency. By modeling inter-fact relationships, DoveScore outperforms existing fine-grained methods by over 8%, providing a more robust solution for long-form text alignment evaluation. Our code and datasets are available at https://github.com/dannalily/DoveScore.

Related papers

• Real-World Summarization: When Evaluation Reaches Its Limits [1.4197924572122094]
  We compare traditional metrics, trainable methods, and LLM-as-a-judge approaches.<n>Our findings reveal that simpler metrics like word overlap surprisingly well with human judgments.<n>Our analysis of real-world business impacts shows incorrect and non-checkable information pose the greatest risks.
  arXiv  Detail & Related papers  (2025-07-15T17:23:56Z)
• Agent-as-Judge for Factual Summarization of Long Narratives [20.3296043006896]
  Large Language Models (LLMs) have demonstrated near-human performance in summarization tasks based on traditional metrics such as ROUGE and BERTScore.<n>Recent advances, such as LLM-as-a-Judge, address the limitations of metrics based on lexical similarity but still exhibit factual inconsistencies.<n>In this work, we introduce NarrativeFactScore, a novel "Agent-as-a-Judge" framework for evaluating and refining summaries.
  arXiv  Detail & Related papers  (2025-01-17T07:23:06Z)
• SAGEval: The frontiers of Satisfactory Agent based NLG Evaluation for reference-free open-ended text [0.848663031844483]
  This paper identifies the need to develop robust evaluation approaches for natural language generation, wherein references/ground labels doesn't exist or isn't amply available. We show that the critiquing Agent is able to rectify scores from LLM evaluators, thereby reducing the need for labeled data even for complex NLG evaluation scenarios.
  arXiv  Detail & Related papers  (2024-11-25T04:07:16Z)
• FactAlign: Long-form Factuality Alignment of Large Language Models [35.067998820937284]
  Large language models have demonstrated significant potential as the next-generation information access engines. We propose FactAlign, a novel alignment framework designed to enhance the factuality of long-form responses. Our experiments on open-domain prompts and information-seeking questions demonstrate that FactAlign significantly improves the factual accuracy of LLM responses.
  arXiv  Detail & Related papers  (2024-10-02T16:03:13Z)
• Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers [121.53749383203792]
  We present a holistic end-to-end solution for annotating the factuality of large language models (LLMs)-generated responses. We construct an open-domain document-level factuality benchmark in three-level granularity: claim, sentence and document. Preliminary experiments show that FacTool, FactScore and Perplexity are struggling to identify false claims.
  arXiv  Detail & Related papers  (2023-11-15T14:41:57Z)
• Fake Alignment: Are LLMs Really Aligned Well? [91.26543768665778]
  This study investigates the substantial discrepancy in performance between multiple-choice questions and open-ended questions. Inspired by research on jailbreak attack patterns, we argue this is caused by mismatched generalization.
  arXiv  Detail & Related papers  (2023-11-10T08:01:23Z)
• 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)
• 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)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)
• Evaluating the Factual Consistency of Large Language Models Through News Summarization [97.04685401448499]
  We propose a new benchmark called FIB(Factual Inconsistency Benchmark) that focuses on the task of summarization. For factually consistent summaries, we use human-written reference summaries that we manually verify as factually consistent. For factually inconsistent summaries, we generate summaries from a suite of summarization models that we have manually annotated as factually inconsistent.
  arXiv  Detail & Related papers  (2022-11-15T18:50:34Z)

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.