Pith. sign in

REVIEW 1 cited by

Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization

Not yet reviewed by Pith; the record is open.

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 2305.13091 v2 pith:PPZALUIT submitted 2023-05-22 cs.CL

classification cs.CL
keywords llmsabstractiveautomaticevaluatorssummarizationchatgptevaluationgpt-4
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

With the recent undeniable advancement in reasoning abilities in large language models (LLMs) like ChatGPT and GPT-4, there is a growing trend for using LLMs on various tasks. One area where LLMs can be employed is as an alternative evaluation metric for complex generative tasks, which generally demands expensive human judges to complement the traditional automatic metrics for various evaluation dimensions such as fluency and consistency. In this work, we conduct extensive analysis to investigate the stability and reliability of LLMs as automatic evaluators for abstractive summarization. We found that while ChatGPT and GPT-4 outperform the commonly used automatic metrics, they are not ready as human replacements due to significant limitations. That is, LLM evaluators rate each candidate system inconsistently and are dimension-dependent. They also struggle to compare candidates with close performance and become more unreliable with higher-quality summaries by obtaining a lower correlation with humans. In other words, with better abstractive summarization systems being introduced at a fast pace, LLMs may result in misleading and unreliable evaluations.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

  1. AutoRAG-LoRA: Hallucination-Triggered Knowledge Retuning via Lightweight Adapters

    cs.CL 2025-07 reject novelty 3.0 of 10

    AutoRAG-LoRA reports a 46.6% relative reduction in classifier-flagged hallucinations on TruthfulQA, but the evaluation uses the same classifier that triggers the corrective training.

Pith tools