mlsanityData to 7 Oct 2026

ISQA: Informative Factuality Feedback for Scientific Summarization

arXiv 2404.13246 ↗First posted 20 Apr 2024cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

We propose Iterative Facuality Refining on Informative Scientific Question-Answering (ISQA) feedbackfootnoteCode is available at urlhttps://github.com/lizekai-richard/isqa, a method following human learning theories that employs model-generated feedback consisting of both positive and negative information. Through iterative refining of summaries, it probes for the underlying rationale of statements to enhance the factuality of scientific summarization. ISQA does this in a fine-grained manner by asking a summarization agent to reinforce validated statements in positive feedback and fix incorrect ones in negative feedback. Our findings demonstrate that the ISQA feedback mechanism significantly improves the factuality of various open-source LLMs on the summarization task, as evaluated across multiple scientific datasets.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 20 Apr 2024.

Builds on

24 of 37 references.

References · 24

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  4. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  6. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  7. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  8. 2022Large Language Models Can Self-Improvecited by 656
  9. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 475
  10. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 376
  11. 2022Generating Sequences by Learning to Self-Correctcited by 271
  12. 2021QuestEval: Summarization Asks for Fact-based Evaluationcited by 241
12 more
  1. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  2. 2022Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectorscited by 103
  3. 2023Learning From Mistakes Makes LLM Better Reasonercited by 97
  4. 2023LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarizationcited by 96
  5. 2019Answers Unite! Unsupervised Metrics for Reinforced Summarization Modelscited by 92
  6. 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 71
  7. 2021CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairscited by 39
  8. 2022Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infillingcited by 38
  9. 2022On Improving Summarization Factual Consistency from Natural Language Feedbackcited by 38
  10. 2022Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarizationcited by 29
  11. 2022UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarizationcited by 15
  12. 2023A Practical Toolkit for Multilingual Question and Answer Generationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Modelscited by 52
  2. 2026ScholarSum: Student-Teacher Abstractive Summarization via Knowledge Graph Reasoning and Reflective Refinementcited by 0