Information Satisfaction: A Reader-Centered Axis for Summarization Evaluation

• URL: http://arxiv.org/abs/2608.14457v1
• Date: Fri, 14 Aug 2026 16:41:23 GMT
• Title: Information Satisfaction: A Reader-Centered Axis for Summarization Evaluation
• Abstract summary: We assess how sensitive popular summarization metrics are to both informational and persona differences.<n>We additionally conduct an expert human evaluation, measuring summary preferences based on information satisfaction.
• Score: 12.756079464205982
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The majority of work on summarization evaluation focuses on general summary quality (e.g., ROUGE, BERTScore) or specific desired properties (e.g., readability, factuality). However, these metrics fail to measure the utility of a summary to an individual user. For example, a biomedical researcher learning about the latest vaccine research will have different informational needs from a family doctor. Query-focused summarization captures part of this need, but in practice, users rarely state everything relevant in a query: a single short query is likely inadequate to distinguish the needs of a researcher from those of a physician. By contrast, a reader's background or persona (their role and expertise) is comparatively stable across queries and recovers much of this missing context, which makes it a practical signal for assessing whether a summary satisfies that reader's needs. In this work, we assess how sensitive popular summarization metrics are to both informational and persona differences, and find that many popular metrics, including strong LLM-as-judge metrics, fail basic perturbation tests of informational content. We additionally conduct an expert human evaluation, measuring summary preferences based on information satisfaction given a specific person's background and use case. We find that both traditional and LLM-based metrics are insufficient measures of information satisfaction and agree poorly with human judgment.

Related papers

• When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs [6.180594609315986]
  Persona prompting is widely used to steer large language models, but its practical value remains unclear.<n>We compare four prompting conditions across 1,140 open-ended questions spanning 38 expert roles and six domains.<n>Role prompting performs best on advisory questions and in domains such as medicine and psychology.
  arXiv  Detail & Related papers  (2026-05-28T06:14:07Z)
• PERCS: Persona-Guided Controllable Biomedical Summarization Dataset [14.620290128367012]
  PERCS is a dataset of biomedical abstracts paired with summaries tailored to four personas.<n>These personas represent different levels of medical literacy and information needs.<n>Technical validation shows clear differences in readability, vocabulary, and content depth across personas.
  arXiv  Detail & Related papers  (2025-12-03T01:13:56Z)
• Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Experts [29.95198868148809]
  We propose a novel methodology that emulates the criteria that professional fact-checkers use to assess the factuality and political bias of an entire outlet.<n>We provide an in-depth error analysis of the effect of media popularity and region on model performance.
  arXiv  Detail & Related papers  (2025-06-14T15:49:20Z)
• The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis [51.046457649151336]
  We propose a perspective on interpretability research grounded in causal mediation analysis.<n>We describe the history and current state of interpretability taxonomized according to the types of causal units (mediators) employed.<n>We discuss the pros and cons of each mediator, providing insights as to when particular kinds of mediators and search methods are most appropriate.
  arXiv  Detail & Related papers  (2024-08-02T17:51:42Z)
• FABLES: Evaluating faithfulness and content selection in book-length summarization [55.50680057160788]
  In this paper, we conduct the first large-scale human evaluation of faithfulness and content selection on book-length documents. We collect FABLES, a dataset of annotations on 3,158 claims made in LLM-generated summaries of 26 books, at a cost of $5.2K USD. An analysis of the annotations reveals that most unfaithful claims relate to events and character states, and they generally require indirect reasoning over the narrative to invalidate.
  arXiv  Detail & Related papers  (2024-04-01T17:33:38Z)
• Is Reference Necessary in the Evaluation of NLG Systems? When and Where? [58.52957222172377]
  We show that reference-free metrics exhibit a higher correlation with human judgment and greater sensitivity to deficiencies in language quality. Our study can provide insight into the appropriate application of automatic metrics and the impact of metric choice on evaluation performance.
  arXiv  Detail & Related papers  (2024-03-21T10:31:11Z)
• Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries [56.31117605097345]
  Large language models (LLMs) have shown the potential to generate accurate clinical text summaries, but still struggle with issues regarding grounding and evaluation.<n>Here, we explore a general mitigation framework using Attribute Structuring (AS), which structures the summary evaluation process.<n>AS consistently improves the correspondence between human annotations and automated metrics in clinical text summarization.
  arXiv  Detail & Related papers  (2024-03-01T21:59:03Z)
• A Literature Review of Literature Reviews in Pattern Analysis and Machine Intelligence [51.26815896167173]
  We present a comprehensive tertiary analysis of PAMI reviews along three complementary dimensions.<n>Our analyses reveal distinctive organizational patterns as well as persistent gaps in current review practices.<n>Finally, our evaluation of state-of-the-art AI-generated reviews indicates encouraging advances in coherence and organization.
  arXiv  Detail & Related papers  (2024-02-20T11:28:50Z)
• A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization [2.8575516056239576]
  Long-form clinical summarization of hospital admissions has real-world significance because of its potential to help both clinicians and patients. We benchmark faithfulness metrics against fine-grained human annotations for model-generated summaries of a patient's Brief Hospital Course.
  arXiv  Detail & Related papers  (2023-03-07T14:57:06Z)
• Understanding the Extent to which Summarization Evaluation Metrics Measure the Information Quality of Summaries [74.28810048824519]
  We analyze the token alignments used by ROUGE and BERTScore to compare summaries. We argue that their scores largely cannot be interpreted as measuring information overlap.
  arXiv  Detail & Related papers  (2020-10-23T15:55:15Z)
• Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning [66.30909748400023]
  We propose to evaluate the summary qualities without reference summaries by unsupervised contrastive learning. Specifically, we design a new metric which covers both linguistic qualities and semantic informativeness based on BERT. Experiments on Newsroom and CNN/Daily Mail demonstrate that our new evaluation method outperforms other metrics even without reference summaries.
  arXiv  Detail & Related papers  (2020-10-05T05:04:14Z)
• Extending Text Informativeness Measures to Passage Interestingness Evaluation (Language Model vs. Word Embedding) [1.2998637003026272]
  This paper defines the concept of Interestingness as a generalization of Informativeness. We then study the ability of state of the art Informativeness measures to cope with this generalization. We prove that the CLEF-INEX Tweet Contextualization 2012 Logarithm Similarity measure provides best results.
  arXiv  Detail & Related papers  (2020-04-14T18:22:48Z)

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.