Pith. sign in

REVIEW 3 cited by

Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.00186 v1 pith:KPAOOSCV submitted 2023-05-31 cs.CL

Paul Roit , Johan Ferret , Lior Shani , Roee Aharoni , Geoffrey Cideron , Robert Dadashi , Matthieu Geist , Sertan Girgin
show 11 more authors
Léonard Hussenot Orgad Keller Nikola Momchev Sabela Ramos Piotr Stanczyk Nino Vieillard Olivier Bachem Gal Elidan Avinatan Hassidim Olivier Pietquin Idan Szpektor
This is my paper
classification cs.CL
keywords entailmentsummariessummarizationtextualconsistencyfactuallygeneratedlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon is emphasized in tasks like summarization, in which the generated summaries should be corroborated by their source article. In this work, we leverage recent progress on textual entailment models to directly address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual entailment rewards to optimize for factual consistency and explore the ensuing trade-offs, as improved consistency may come at the cost of less informative or more extractive summaries. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience, and conciseness of the generated summaries.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Training Language Models to Self-Correct via Reinforcement Learning

    cs.LG 2024-09 unverdicted novelty 6.0 of 10

    SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.

  2. Chain-of-Verification Reduces Hallucination in Large Language Models

    cs.CL 2023-09 unverdicted novelty 6.0 of 10

    Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.

  3. RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

    cs.CL 2023-09 conditional novelty 6.0 of 10

    RLAIF matches RLHF on summarization and dialogue tasks, with a direct-RLAIF variant achieving superior results by using LLM rewards directly during training.

Pith tools