Papers by Xiawu Zheng

5 papers
Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach: They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome: The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.
Automated Fine-Grained Mixture-of-Experts Quantization (2025.findings-acl)

Copied to clipboard

Challenge: specialized quantization framework for Mixture of Experts architectures is inadequate for model compression.
Approach: They propose a specialized quantization framework for Mixture of Experts architectures . they find that expert networks exhibit distinctive channel-wise outlier distributions ."
Outcome: The proposed framework improves on the Mixtral-8x7b-v0.1 architecture while maintaining minimal computational overhead.
ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization (2026.findings-acl)

Copied to clipboard

Challenge: Recent LLM-based systems require simulation of algorithm flow and video rendering constraints.
Approach: They propose a paradigm that decouples algorithm execution from rendering.
Outcome: The proposed paradigm reduces execution success rates, element overlap, and inter-frame inconsistencies.
Learning Transition Patterns by Large Language Models for Sequential Recommendation (2025.coling-main)

Copied to clipboard

Challenge: Extensive experiments on six real-world datasets show our approach outperforms the best baselines by 7.33% in NDCG@10, 4.65% in Recall@10 and 8.42% in MRR.
Approach: They propose a framework for mapping sequential item texts to sequential item IDs that incorporates multi-query input and item linear projection to model conditional probability distribution of items.
Outcome: The proposed framework outperforms baseline models on six real-world datasets by 7.33% and 4.65% respectively.
Relaxing the Constraints: A Dual-Importance Projection Mechanism for Lifelong Model Editing (2026.findings-acl)

Copied to clipboard

Challenge: Existing knowledge editing methods rely on strict orthogonal projection to preserve previously edited knowledge, but this constraint limits gradient expressiveness, resulting in degradation of model generalization and overall performance as the number of edits increases.
Approach: They propose a method that leverages Singular Value Decomposition to identify critical gradient subspaces and introduces a dual mechanism comprising "accumulated importance" and "projection importance"
Outcome: Extensive experiments on five mainstream LLMs show that the proposed method achieves an average comprehensive performance improvement of 10.36% and effectively maintains the model’s general capabilities on downstream tasks.

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