Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • Home
  • Search Results
  • Page 1 of 12

Search for: All records

Creators/Authors contains: "Zhao, T."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. ; ; ; (, ArXivorg)
    Free, publicly-accessible full text available August 11, 2027
  2. ; ; ; ; ; ; (, SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’26))
    Free, publicly-accessible full text available July 20, 2027
  3. ; ; ; (, Conference on Neural Information Processing Systems (NeurIPS) 2025)
    Free, publicly-accessible full text available December 30, 2026
  4. ; ; ; ; ; ; ; ; (, arXiv)
    Free, publicly-accessible full text available November 21, 2026
  5. ; ; (, Proc. International Conference on Database Systems for Advanced Applications (DASFAA))
    Accepted Manuscript Full Text Available
  6. ; ; (, Proc. International Conference on Database Systems for Advanced Applications)
    Accepted Manuscript Full Text Available
  7. ; ; ; ; ; ; ; (, Proceedings of Machine Learning Research)
    Large language models (LLMs) have achieved impressive performance but face high computational costs and latency, limiting their deployment in resource-constrained settings. In contrast, small-scale LLMs (SLMs) are more efficient yet struggle to capture evolving real-world knowledge. Retrieval-augmented generation (RAG) helps by integrating external knowledge, but imperfect retrieval can introduce distracting noise that misleads SLMs. We propose {\name}, a robust RAG framework for SLMs via Margin-aware Preference Optimization. {\name} employs multi-turn prompting for detailed reasoning, rejection sampling for high-quality explanations, and contrastive preference selection to refine responses by maximizing the likelihood gap between preferred and non-preferred outputs. 
    more » « less
    Accepted Manuscript Full Text Available
  8. ; ; ; ; ; (, Proceedings of the International World Wide Web Conference (WWW’25))
    Accepted Manuscript Full Text Available
  9. ; ; ; ; ; (, Annual Conference of the Nations of the Americas Chapter of the ACL (NAACL).)
    Accepted Manuscript Full Text Available
  10. ; ; ; ; ; ; (, Conference on Language Modeling)
    Accepted Manuscript Full Text Available