most citedMechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units

7 citations · 7 across the 1 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL20267 cited

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units

Jianhui Chen, Yuzhang Luo, Liangming Pan

While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive. We introduce Mechanistic Data Attribution (M…

cs.CL2026

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures

Yi Hu, Jiaqi Gu, Ruxin Wang +6

Reinforcement learning (RL) has catalyzed the emergence of Large Reasoning Models (LRMs) that have pushed reasoning capabilities to new heights. While their performance has garnere…

cs.CL2025

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

Jianhui Chen, Xiaozhi Wang, Zijun Yao +3

Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper,…

cs.CL2025

Are Reasoning Models More Prone to Hallucination?

Zijun Yao, Yantao Liu, Yanxu Chen +5

Recently evolved large reasoning models (LRMs) show powerful performance in solving complex tasks with long chain-of-thought (CoT) reasoning capability. As these LRMs are mostly de…

cs.CL2024

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

Jifan Yu, Xiaozhi Wang, Shangqing Tu +32

The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations. Rather than merely exploring the breadth of LLM abilities, we believe meticu…

cs.CL2024

MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation

Xiaozhi Wang, Hao Peng, Yong Guan +9

Understanding events in texts is a core objective of natural language understanding, which requires detecting event occurrences, extracting event arguments, and analyzing inter-eve…