Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation frameworks for large language models focus on isolated aspects like * Equal contribution. |
| Approach: | They evaluate ICAT, an evaluation framework for measuring coverage of diverse factual information in long-form text generation. |
| Outcome: | The evaluation framework is based on three implementations with different assumptions on availability of aspects and alignment method. |
Similar Papers
Towards Effective Extraction and Evaluation of Factual Claims (2025.acl-long)
Copied to clipboard
| Challenge: | Lack of a standardized evaluation framework impedes assessment and comparison of claim extraction methods. |
| Approach: | They propose a framework for evaluating claim extraction in the context of fact-checking . they also introduce Claimify, an LLM-based claim extraction method . |
| Outcome: | The proposed evaluation framework outperforms existing methods in the evaluation of claim extraction methods. |
Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) produce incomplete or selectively omit key information . omissions of key information or misrepresentation of conflicting evidence can cause harm . |
| Approach: | They propose a method that decomposes texts into atomic statements and uses natural language inference to identify missing facts and a Q A-based metric that extracts question-answer pairs and compares responses across sources. |
| Outcome: | The proposed evaluation metrics show they perform better than more complex metrics, but at a cost. |
FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation (2023.emnlp-main)
Copied to clipboard
Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Koh, Mohit Iyyer, Luke Zettlemoyer, Hannaneh Hajishirzi
| Challenge: | Evaluating the factuality of long-form text generated by large language models (LMs) is non-trivial because (1) generations often contain a mixture of supported and unsupported pieces of information, making binary judgments of quality inadequate and (2) human evaluation is time-consuming and costly. |
| Approach: | They introduce a new evaluation that breaks a generation into a series of atomic facts and computes the percentage of atom facts supported by a reliable knowledge source. |
| Outcome: | The proposed model breaks a generation into atomic facts and computes the percentage of atomic fact supported by a reliable knowledge source. |
VeriScore: Evaluating the factuality of verifiable claims in long-form text generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing metrics for evaluating the factuality of long-form text assume that every claim is verifiable. |
| Approach: | They propose a metric to evaluate factuality in diverse long-form generation tasks . they use open-weight language models to extract verifiable and unverifiably content . |
| Outcome: | The proposed metric can be implemented with either closed or fine-tuned open-weight language models. |
A Tale of Evaluating Factual Consistency: Case Study on Long Document Summarization Evaluation (2025.findings-acl)
Copied to clipboard
| Challenge: | Despite the recent progress for summarization models in producing fluent summaries, they still encounter challenges when long sequences of generated texts and inputs (over thousands of words) need to be evaluated. |
| Approach: | They conduct a systematic analysis of factual-consistency evaluation systems across four long-document datasets and examine the relationship between sentence-level and summary-level model performance. |
| Outcome: | The proposed models can achieve higher recall in error detection for older summaries, yet struggle with false positives and fine-grained error detection. |
How Does Response Length Affect Long-Form Factuality (2025.findings-acl)
Copied to clipboard
| Challenge: | Despite growing attention to LLM factuality, the effect of response length on factual accuracy remains underexplored. |
| Approach: | They propose an automatic and bi-level long-form factuality evaluation framework which achieves high agreement with human annotations while being cost-effective. |
| Outcome: | The proposed framework achieves high agreement with human annotations while being cost-effective. |
FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in text summarization have shown remarkable performance, but a significant number of summaries exhibit factual inconsistencies, such as hallucinations. |
| Approach: | They propose a factuality-oriented metric that evaluates text summarization for accuracy . they use a human annotation process to examine the accuracy of automatically generated summaries . |
| Outcome: | The proposed metric sets a new state-of-the-art on AGGREFACT, the de-facto benchmark for factuality evaluation. |
ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Evaluating personalized text generated by large language models is challenging, as only the LLM user, i.e. prompt author, can reliably assess the output. |
| Approach: | They propose an explainable reference-based evaluation framework that leverages an LLM to extract atomic aspects and their evidences from the generated and reference texts, match the aspects, and evaluate their alignment based on content and writing style. |
| Outcome: | The proposed framework achieves a 7.2% improvement in alignment with human judgments compared to the state-of-the-art evaluation methods. |
Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing factuality metrics cannot evaluate paragraphs with ambiguous entities, authors show . |
| Approach: | They propose a new metric to evaluate the factuality of long-form generations from large language models. |
| Outcome: | The proposed metric can assess the factuality of people biographies with entity ambiguity better than FActScore. |
LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability (2025.findings-emnlp)
Copied to clipboard
Zikai Xiao, Fei Huang, Jianhong Tu, Jianhui Wei, Wen Ma, Yuxuan Zhou, Jian Wu, Bowen Yu, Zuozhu Liu, Junyang Lin
| Challenge: | Existing benchmarks for long-form generation assess real-world queries with hard-to-verify metrics or use synthetic setups that overlook real-life intricacies. |
| Approach: | They propose a new approach that balances verifiable and real-world assessment with Target-Anchored Evaluation. |
| Outcome: | The proposed model balances real-world and verifiable assessment with Target-Anchored Evaluation (TAE) it generates queries, textual materials, and anchors based on verifier targets within real-life scenarios . |