Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response
원문 초록
LLMs (large language models) such as ChatGPT have shown remarkable language understanding and generation capabilities. Although reference-free evaluators based on LLMs show better human alignment than traditional reference-based evaluators, there are many challenges in using reference-free evaluators based on LLMs. Reference-free evaluators are more suitable for open-ended examples with different semantics responses. But not all examples are open-ended. For closed-ended examples with unique correct semantic response, reference-free evaluators will still consider it high quality when giving a response that is inconsistent with the facts and the semantic of reference. In order to comprehensively evaluate the reliability of evaluators based on LLMs, we construct two adversarial meta-evaluation dialogue generation datasets KdConv-ADV and DSTC7-ADV based on KdConv and DSTC7-AVSD, respectively. Compared to previous meta-evaluation benchmarks, KdConv-ADV and DSTC7-ADV are much more challenging since they requires evaluators to be able to reasonably evaluate closed-ended examples with the help of external knowledge or even its own knowledge. Empirical results show that the ability of LLMs to identify unreasonable responses is insufficient. There are risks in using eference-free evaluators based on LLMs to evaluate the quality of dialogue responses.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
SDialog: A Python Toolkit for Synthetic Dialogue Generation and Analysis
Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment
Efficient Tuning of Large Language Models for Knowledge-Grounded Dialogue Generation
VisTai: Benchmarking Vision-Language Models for Traditional Chinese in Taiwan
SAGE: Steering and Refining Dialog Generation with State-Action Augmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.