Abstract
My primary research interests lie in evaluating and improving the faithfulness of language model-based text generation systems. Recent advances in large language models (LLMs) such as GPT-4 and Llama have enabled the wide adoption of LLMs in various aspects of natural language processing (NLP). Despite their widespread use, LLMs still suffer from the problem of hallucination, limiting the practicality of deploying such systems in use cases where being factual and faithful is of critical importance. My research specifically aims to evaluate and improve the faithfulness, i.e. the factual alignment between the generated text and a given context, of text generation systems. By developing techniques to reliably evaluate, label, and improve generation faithfulness, we can enable wider adoption of dialog systems that need to converse with human users using accurate information.- Anthology ID:
- 2024.yrrsds-1.14
- Volume:
- Proceedings of the 20th Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems
- Month:
- September
- Year:
- 2024
- Address:
- Kyoto, Japan
- Editors:
- Koji Inoue, Yahui Fu, Agnes Axelsson, Atsumoto Ohashi, Brielen Madureira, Yuki Zenimoto, Biswesh Mohapatra, Armand Stricker, Sopan Khosla
- Venues:
- YRRSDS | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 37–39
- Language:
- URL:
- https://preview.aclanthology.org/remove-affiliations/2024.yrrsds-1.14/
- DOI:
- Cite (ACL):
- Sicong Huang. 2024. Toward Faithful Dialogs: Evaluating and Improving the Faithfulness of Dialog Systems. In Proceedings of the 20th Workshop of Young Researchers' Roundtable on Spoken Dialogue Systems, pages 37–39, Kyoto, Japan. Association for Computational Linguistics.
- Cite (Informal):
- Toward Faithful Dialogs: Evaluating and Improving the Faithfulness of Dialog Systems (Huang, YRRSDS 2024)
- PDF:
- https://preview.aclanthology.org/remove-affiliations/2024.yrrsds-1.14.pdf