activity
20232026
most citedWhen does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks

5 citations · 8 across the 5 of their papers we have counts for

collaborators

7 papers

cs.CL2026

From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution

Yuzhang Luo, Chenpeng Wang, Jianhui Chen +1

Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value depends on both which examples are selected and how they ar…

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.CL2026

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.CL20253 cited

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

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.LG2024

Root Causing Prediction Anomalies Using Explainable AI

Ramanathan Vishnampet, Rajesh Shenoy, Jianhui Chen +1

This paper presents a novel application of explainable AI (XAI) for root-causing performance degradation in machine learning models that learn continuously from user engagement dat…