Papers › HaRiM^+: Evaluating Summary Quality with Hallucination Risk

HaRiM^+: Evaluating Summary Quality with Hallucination Risk

22 Nov 2022arXiv:2211.12118archive 2025-07-28

Seonil Son, Junsoo Park, Jeong-in Hwang, Junghwa Lee, Hyungjong Noh, Yeonsoo Lee

One of the challenges of developing a summarization model arises from the difficulty in measuring the factual inconsistency of the generated text. In this study, we reinterpret the decoder overconfidence-regularizing objective suggested in (Miao et al., 2021) as a hallucination risk measurement to better estimate the quality of generated summaries. We propose a reference-free metric, HaRiM+, which only requires an off-the-shelf summarization model to compute the hallucination risk based on token likelihoods. Deploying it requires no additional training of models or ad-hoc modules, which usually need alignment to human judgments. For summary-quality estimation, HaRiM+ records state-of-the-art correlation to human judgment on three summary-quality annotation sets: FRANK, QAGS, and SummEval. We hope that our work, which merits the use of summarization models, facilitates the progress of both automated evaluation and generation of summary.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ncsoft/harim_plus officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automated Writing EvaluationDecoderHallucinationText Summarization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections