Papers by Yuwei Hou

2 papers
CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations (2026.findings-acl)

Copied to clipboard

Challenge: LLM-empowered agent simulations generate rich, adaptive, and often nonlinear interaction patterns.
Approach: They propose an automated Causal discovery framework for LLM agent simulations that converts mechanistic hypotheses into computable factors and learns a compact causal representation centered on an emergent target.
Outcome: Experiments across four emergent settings demonstrate the promise of CAMO.
FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for realistic financial analysis fail to capture realistic financial situations involving cross-document retrieval, multi-page evidence integration, and diverse analytical tasks.
Approach: They propose a multi-modal financial RAG benchmark that evaluates large language models in realistic financial analysis settings.
Outcome: The proposed framework achieves the strongest overall performance across all models.

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