Papers with Fine-tuning language models

2 papers
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in instruction-tuning datasets focus on specific tasks like mathematical or logical reasoning.
Approach: They propose to use synthetic dialogues to help language models remain focused on the subject at hand during task-oriented interactions.
Outcome: The proposed dataset improves language models' ability to maintain topical coherence compared to general-purpose instruction-tuned LLMs like gpt-4-turbo and Mixtral-Instruct.
NSF-SciFy: Mining the NSF Awards Database for Scientific Claims (2026.acl-long)

Copied to clipboard

Challenge: NSF-SciFy contains 2.8 million claims from 400,000 abstracts spanning all science and mathematics disciplines.
Approach: They propose to use a dataset to extract scientific claims from National Science Foundation award abstracts and to use it to refine language models.
Outcome: The proposed method improves non-technical abstract generation, claim extraction, and investigation proposal extraction tasks while maintaining high precision and lower recall.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations