Papers by Hongming Cai

4 papers
MergeIT: From Selection to Merging for Efficient Instruction Tuning (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for instruction tuning rely on LLMs to score instruction quality . existing methods rely only on Llms to rank instruction quality, but this approach is expensive and time-consuming .
Approach: They propose a novel LLM-based Merging strategy for better Instruction Tuning that shifts the focus from selection to synthesis.
Outcome: The proposed method reduces time and computational cost while preserving diversity and reducing redundancy.
GeoHard: Towards Measuring Class-wise Hardness through Modelling Class Semantics (2024.findings-acl)

Copied to clipboard

Challenge: Recent advances in measuring hardness-wise properties of data guide language models in sample selection within low-resource scenarios.
Approach: They propose to use class-wise hardness to measure class-specific properties of data in the semantic embedding space by modeling class geometry in the . semantic embeddining space.
Outcome: The proposed method surpasses instance-level metrics by over 59 percent on Pearson‘s correlation on measuring class-wise hardness.
MixGR: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity (2024.emnlp-main)

Copied to clipboard

Challenge: Recent studies show the importance of document retrieval in the scientific domain.
Approach: They propose a zero-shot approach to measure query-document similarity using atomic components in queries and documents to combine them into a united score.
Outcome: The proposed approach outperforms previous document retrieval methods by 24.7%, 9.8%, and 6.9% on nDCG@5 with unsupervised, supervised, and LLM-based retrievers.
KaeDe: Progressive Generation of Logical Forms via Knowledge-Aware Question Decomposition for Improved KBQA (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for answering natural language questions are difficult to generate . lack of a logical form for complex graphs can negatively impact overall performance .
Approach: They propose a generate-then-retrieve method that converts questions into structured LF queries . they propose to combine knowledge-aware question decomposition and progressive LF generation .
Outcome: The proposed method achieves state-of-the-art (SOTA) performance on WebQuestionSP and ComplexWebQuestions benchmarks.

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