@UMassBioNLP

The Biomedical NLP group co-located at the University of Massachusetts Amherst and Lowell. Led by Dr. Hong Yu. @UMass_NLP @manningcics @UMassLowell #NLProc

 UMass
bio-nlp.github.io/
Joined August 2024
  • Tweets47
  • Following17
  • Followers34
18Media
🎉 New paper alert! #EMNLP24 SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization 🔗 arxiv.org/abs/2402.13919 Work done by @PrakamyaMishra @YaoZonghai @vashisht51, Feiyun Ouyang, Beining Wang, Vidhi Dhaval Mody, and Prof. Hong Yu (0/N)
1
2
3
8
2,392
more replies
📊 External Evaluation: We compared STF-trained models vs. DPO/SALT-trained ones and found that GPT-2 & Llama2 excelled with GPT-4 edits over GPT-3.5. SALT's granular feedback improved alignment, with GPT-2 showing higher ROUGEL in High→Low training and stable factuality. (13/N)
1
1
125
🔔 Conclusion: This study leverages synthetic edit feedback to improve factual accuracy in clinical summarization using DPO and SALT techniques. Our approach demonstrates the effectiveness of LLM-based edit data in enhancing the reliability of clinical NLP applications. (14/N)
1
79
🎉 New paper alert! Large Language Models are In-context Teachers for Knowledge Reasoning #EMNLP24 finding 🔗 Read the paper: arxiv.org/abs/2311.06985 Work done by @jcz12856876 @YaoZonghai @YangZhichaoNLP and Prof. Hong Yu #BioNLP #InstructionTuning (0/N)
1
2
2
7
3,286
more replies
🧪 To verify the causality, we propose teach-back to align the teacher’s rationales with the student’s self-explanations. Experiments show that teach-back can greatly improve the in-context teaching ability of a model. (7/N)
1
72
📊 Results show that LLMs’ self-explanations are quite different from Human-craft CoTs and have less variance, though using LLMs’ self-explanations for ICL leads to better performance. We also question treating human-craft CoTs as the gold standard for in-context exemplars. (8/N)
59
Load more