CoChat

Benchmarking Large Language Models for News Summarization

Open access
Zhang, Tianyi, Ladhak, Faisal, Durmus, Esin, Liang, Percy, McKeown, Kathleen, Hashimoto, Tatsunori B. · 2024 · Transactions of the Association for Computational Linguistics

The DOI matches its Crossref record; 86 of the 86 references it cites were found in a registry or an index.

Abstract

Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood. By conducting a human evaluation on ten LLMs across different pretraining methods, prompts, and model scales, we make two important observations. First, we find instruction tuning, not model size, is the key to the LLM’s zero-shot summarization capability. Second, existing studies have been limited by low-quality references, leading to underestimates of human performance and lower few-shot and finetuning performance. To better evaluate LLMs, we perform human evaluation over high-quality summaries we collect from freelance writers. Despite major stylistic differences such as the amount of paraphrasing, we find that LLM summaries are judged to be on par with human written summaries.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1162/tacl_a_00632

Cites

86 of 86 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 86 references

Research works printed but not linked: 1

  1. Conroy, 2006, Back to basics: Classy 2006, 10.12968/sece.2006.11.755s · doi:10.12968/sece.2006.11.755s

Cited by

Items 101–200 of 427

Metadata

Authors
Zhang, T., Ladhak, F., Durmus, E., Liang, P., McKeown, K., & Hashimoto, T. B.
Affiliations
  • Stanford University (US)
  • Columbia University (US)
Corresponding author
  • Zhang, Tianyi
  • Ladhak, Faisal
Venue
Transactions of the Association for Computational Linguistics
Publisher
MIT Press
Published
2024
Volume
12
Pages
39-57
ISSN
2307-387X (ISSN-L)
OpenAlex
W4391494845
Cited by
415
References
79
Citations by year
2026: 108 · 2025: 165 · 2024: 96
FWCI
54.46
Type
journal article
Language
en
Open access
Locations
  • Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
Open Philanthropy Project
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Advanced Text Analysis Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
large language models, news summarization, automatic summarization, human evaluation, instruction tuning, zero-shot summarization, fine-tuning, model size, human-written summaries, paraphrase, freelance writers

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.