Image de couverture de livre

Identifying Good and Bad Neurons for Task-Level Controllable LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Wenjie, Pang, Guansong, Qiao, Hezhe, Gao, Debin, Lo, David
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection
par: Qiao, Hezhe, et autres
Publié: (2023)

How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?
par: Lo, Leo Yu-Ho, et autres
Publié: (2024)

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains
par: Yi, Zihao, et autres
Publié: (2025)

The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism
par: Song, Yifan, et autres
Publié: (2024)

AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection
par: Qiao, Hezhe, et autres
Publié: (2025)

GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers
par: Ai, Guoguo, et autres
Publié: (2024)

When Bad Data Leads to Good Models
par: Li, Kenneth, et autres
Publié: (2025)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
par: Xia, Heming, et autres
Publié: (2025)

Assessing Good, Bad and Ugly Arguments Generated by ChatGPT: a New Dataset, its Methodology and Associated Tasks
par: Rocha, Victor Hugo Nascimento, et autres
Publié: (2024)

The Good, The Bad, and Why: Unveiling Emotions in Generative AI
par: Li, Cheng, et autres
Publié: (2023)

SCALM: Detecting Bad Practices in Smart Contracts Through LLMs
par: Li, Zongwei, et autres
Publié: (2025)

FADE: Why Bad Descriptions Happen to Good Features
par: Puri, Bruno, et autres
Publié: (2025)

H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
par: Gao, Cheng, et autres
Publié: (2025)

The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors
par: Sadallah, Abdelrahman, et autres
Publié: (2025)

Where Fake Citations Are Made: Tracing Field-Level Hallucination to Specific Neurons in LLMs
par: Chen, Yuefei, et autres
Publié: (2026)

VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
par: Qiao, Hezhe, et autres
Publié: (2026)

Automated Evaluation can Distinguish the Good and Bad AI Responses to Patient Questions about Hospitalization
par: Soni, Sarvesh, et autres
Publié: (2025)

Small Edits, Big Consequences: Telling Good from Bad Robustness in Large Language Models
par: Ismailov, Altynbek, et autres
Publié: (2025)

Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?
par: Chen, Pinzhen, et autres
Publié: (2024)

Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection
par: Hu, Beizhe, et autres
Publié: (2023)

Deep Graph Anomaly Detection: A Survey and New Perspectives
par: Qiao, Hezhe, et autres
Publié: (2024)

Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks
par: Pires, Ramon, et autres
Publié: (2026)

STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs
par: An, Sungeun, et autres
Publié: (2026)

Simulation, Modelling and Classification of Wiki Contributors: Spotting The Good, The Bad, and The Ugly
par: Méndez, Silvia García, et autres
Publié: (2024)

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
par: Zeng, Shenglai, et autres
Publié: (2024)

Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?
par: Lin, Fei, et autres
Publié: (2025)

Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora
par: Kim, Yungi, et autres
Publié: (2024)

AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
par: Mazumder, Aritra, et autres
Publié: (2026)

Can LLMs Ask Good Questions?
par: Zhang, Yueheng, et autres
Publié: (2025)

Can GNN be Good Adapter for LLMs?
par: Huang, Xuanwen, et autres
Publié: (2024)

Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generation
par: Huang, Wei, et autres
Publié: (2026)

Dissecting Role Cognition in Medical LLMs via Neuronal Ablation
par: Liang, Xun, et autres
Publié: (2025)

Self-Supervised Spatial-Temporal Normality Learning for Time Series Anomaly Detection
par: Chen, Yutong, et autres
Publié: (2024)

Can LLMs be Good Graph Judge for Knowledge Graph Construction?
par: Huang, Haoyu, et autres
Publié: (2024)

Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability
par: Zhao, Xin, et autres
Publié: (2024)

DHP Benchmark: Are LLMs Good NLG Evaluators?
par: Wang, Yicheng, et autres
Publié: (2024)

Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Information
par: Li, Yingya, et autres
Publié: (2024)

Position: LLMs Can be Good Tutors in English Education
par: Ye, Jingheng, et autres
Publié: (2025)

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
par: Zhang, Zhuoxuan, et autres
Publié: (2025)

Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward
par: Kumar, Shashi, et autres
Publié: (2024)