TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization.
Liyan TangIgor ShalyminovAmy Wing-mei WongJon BurnskyJake W. VincentYuan YangSiffi SinghSong FengHwanjun SongHang SuLijia SunYi ZhangSaab MansourKathleen McKeownPublished in: NAACL-HLT (2024)
Keyphrases
- multi document summarization
- automatic summarization
- topic segmentation
- spoken dialogue systems
- natural language
- dialogue system
- neural network
- automatic evaluation
- opinion summarization
- man machine
- mixed initiative
- document summaries
- related topics
- interactive systems
- human machine
- news articles
- focused crawler
- natural language dialogue