News

[Apr. 2025] Excited that SiReRAG is accepted by ICLR 2025! My collaborators are presenting it in person during Poster Session 1 (#61 at Hall 3 + Hall 2B). I am happy to discuss research on RAG, LLMs compression, and large reasoning models virtually.

[Apr. 2025] Our benchmarking paper on compressed large reasoning models (LRMs) is online, entitled When Reasoning Meets Compression: Benchmarking Compressed Large Reasoning Models on Complex Reasoning Tasks. We provide detailed analysis on quantized, distilled, and pruned reasoning models!

[Dec. 2024] Our RAG indexing paper on similar and related corpus contents is online, entitled SiReRAG: Indexing Similar and Related Information for Multihop Reasoning. Our paper consistently outperforms current indexing works on multihop datasets!

[Sept. 2024] One paper on LLMs as paper reviewers and area chairs has been accepted to EMNLP 2024.

[Aug. 2024] One paper on self-correction of LLMs has been accepted to TACL 2024.

[July 2024] One paper on error detection benchmark of LLMs has been accepted to COLM 2024.

[June 2024] Our survey paper on self-correction of LLMs is online, entitled When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs. Feel free to check it out!

[Apr. 2024] I will join Salesforce AI Research as a Research Intern at Palo Alto, CA in summer 2024!

[Apr. 2024] Our paper on error detection benchmark of LLMs is online, entitled Evaluating LLMs at Detecting Errors in LLM Responses. Feel free to check it out!

[Mar. 2024] Two papers on LLMs compression and LLMs summarization have been accepted to NAACL 2024.

[Feb. 2024] Our FaMeSumm paper has been reported by Penn State News and other external sites.

[Feb. 2024] One paper on chemistry-oriented OCR has been accepted to LREC-COLING 2024.

[Jan. 2024] Our survey paper on resource-efficient LLMs is online, entitled Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models. Feel free to check it out!

[Dec. 2023] Presented our FaMeSumm paper at EMNLP 2023 in Singapore.

[Nov. 2023] Our paper on fair abstractive summarization of diverse perspectives is online. Feel free to check it out!