works on
benchmark evaluation 1causal tracing 1large language models 1model editing 1temporal reasoning 1

From the 1 of 24 linked papers with an AI index.

activity
20242026
most citedSkillNet: Create, Evaluate, and Connect AI Skills

1 citations · 1 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

PRISM Edit: One Vector for All Temporal Answers

Chen Huang, Qi Zheng, Ruiqin Zheng +2

The paper proposes PRISM Edit, a method that updates large language models to handle changing temporal facts by learning a single representation that can be modulated for different…

cs.LG2026

From Data to Behavior: Predicting Unintended Model Behaviors Before Training

Mengru Wang, Zhenqian Xu, Junfeng Fang +4

Large Language Models (LLMs) can acquire unintended biases from seemingly benign training data even without explicit cues or malicious content. Existing methods struggle to detect…