Copertina

Dissecting Role Cognition in Medical LLMs via Neuronal Ablation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liang, Xun, Lai, Huayi, Wang, Hanyu, Zhang, Wentao, Zhang, Linfeng, Chen, Yanfang, Xiong, Feiyu, Li, Zhiyu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism
di: Lv, Bo, et al.
Pubblicazione: (2025)

MemFactory: Unified Inference & Training Framework for Agent Memory
di: Guo, Ziliang, et al.
Pubblicazione: (2026)

RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents
di: Lai, Huayi, et al.
Pubblicazione: (2026)

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
di: Liu, Hongyi, et al.
Pubblicazione: (2026)

Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT
di: Tao, Zhen, et al.
Pubblicazione: (2024)

How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective
di: Zhang, Shimao, et al.
Pubblicazione: (2025)

The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
di: Shen, Lingfeng, et al.
Pubblicazione: (2024)

Bootstrapping Cognitive Agents with a Large Language Model
di: Zhu, Feiyu, et al.
Pubblicazione: (2024)

Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support
di: Wang, Guoxin, et al.
Pubblicazione: (2025)

A Method for Constructing a Digital Transformation Driving Mechanism Based on Semantic Understanding of Large Models
di: Liu, Huayi
Pubblicazione: (2026)

SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models
di: Liang, Xun, et al.
Pubblicazione: (2025)

Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving
di: Zhou, Yuxuan, et al.
Pubblicazione: (2025)

Can LLMs be Good Graph Judge for Knowledge Graph Construction?
di: Huang, Haoyu, et al.
Pubblicazione: (2024)

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
di: Zhang, Zhuoxuan, et al.
Pubblicazione: (2025)

Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
di: Chen, Yingjian, et al.
Pubblicazione: (2025)

Semantic Refinement with LLMs for Graph Representations
di: Thapaliya, Safal, et al.
Pubblicazione: (2025)

Unlocking Recursive Thinking of LLMs: Alignment via Refinement
di: Zhang, Haoke, et al.
Pubblicazione: (2025)

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective
di: Chandna, Bhavik, et al.
Pubblicazione: (2025)

Dissecting Human and LLM Preferences
di: Li, Junlong, et al.
Pubblicazione: (2024)

H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
di: Gao, Cheng, et al.
Pubblicazione: (2025)

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
di: Zhang, Xiaoying, et al.
Pubblicazione: (2024)

Eye of Judgement: Dissecting the Evaluation of Russian-speaking LLMs with POLLUX
di: Martynov, Nikita, et al.
Pubblicazione: (2025)

Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learning
di: Zhang, Xiaotian, et al.
Pubblicazione: (2025)

Can LLMs Convert Graphs to Text-Attributed Graphs?
di: Wang, Zehong, et al.
Pubblicazione: (2024)

TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration
di: Li, Weiya, et al.
Pubblicazione: (2025)

Identifying Good and Bad Neurons for Task-Level Controllable LLMs
di: Li, Wenjie, et al.
Pubblicazione: (2026)

InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
di: Du, Yaxin, et al.
Pubblicazione: (2025)

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models
di: Zhu, Junyi, et al.
Pubblicazione: (2024)

MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
di: Li, Jiazheng, et al.
Pubblicazione: (2025)

Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study
di: Zhou, Yujun, et al.
Pubblicazione: (2025)

Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?
di: Liang, Qingyuan, et al.
Pubblicazione: (2025)

NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism
di: Li, Miao, et al.
Pubblicazione: (2024)

Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors
di: Yang, Hao, et al.
Pubblicazione: (2025)

Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations
di: Liu, Zijie, et al.
Pubblicazione: (2025)

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis
di: Zhao, Yufeng, et al.
Pubblicazione: (2025)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
di: Pan, Birong, et al.
Pubblicazione: (2025)

PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness
di: Wang, Zekun, et al.
Pubblicazione: (2024)

Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
di: Zhang, Xuemiao, et al.
Pubblicazione: (2025)

Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
di: Zhu, Yu, et al.
Pubblicazione: (2024)

Where Fake Citations Are Made: Tracing Field-Level Hallucination to Specific Neurons in LLMs
di: Chen, Yuefei, et al.
Pubblicazione: (2026)