Papers by Wenxiang Geng

1 papers
The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) exhibit a critical failure mode: they exhibit brittle reasoning capabilities on out-of-distribution tasks.
Approach: They propose a framework bridging Structural Causal Models and the Information Bottleneck principle to explain this paradox.
Outcome: The proposed framework bridges the framework between SCM and IB principles to explain the problem.

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