Cover Image

Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Leng, Yongqi, Xiong, Deyi
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL
by: Yang, Lei, et al.
Published: (2026)

Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
by: Chen, Yan-Lun, et al.
Published: (2025)

TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination
by: Naim, Omar, et al.
Published: (2025)

Exploring the Limits of Model Compression in LLMs: A Knowledge Distillation Study on QA Tasks
by: Datta, Joyeeta, et al.
Published: (2025)

Zero-Shot Detection of LLM-Generated Code via Approximated Task Conditioning
by: Ashkenazi, Maor, et al.
Published: (2025)

Dynamic Prompt Fusion for Multi-Task and Cross-Domain Adaptation in LLMs
by: Hu, Xin, et al.
Published: (2025)

Can we Soft Prompt LLMs for Graph Learning Tasks?
by: Liu, Zheyuan, et al.
Published: (2024)

Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws
by: Jha, Akshita, et al.
Published: (2024)

Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection
by: Mavi, Vaibhav, et al.
Published: (2025)

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders
by: Wang, Shun, et al.
Published: (2025)

TOFU: A Task of Fictitious Unlearning for LLMs
by: Maini, Pratyush, et al.
Published: (2024)

Balancing Synthetic Data and Replay for Enhancing Task-Specific Capabilities
by: Spiegelhalter, Urs, et al.
Published: (2025)

Multi-Task Model Merging via Adaptive Weight Disentanglement
by: Xiong, Feng, et al.
Published: (2024)

From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When
by: Wibisono, Kevin Christian, et al.
Published: (2024)

Polynomial Regression as a Task for Understanding In-context Learning Through Finetuning and Alignment
by: Wilcoxson, Max, et al.
Published: (2024)

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
by: Zhong, Shanshan, et al.
Published: (2026)

Understanding Generalization in Role-Playing Models via Information Theory
by: Li, Yongqi, et al.
Published: (2025)

Towards Specialized Generalists: A Multi-Task MoE-LoRA Framework for Domain-Specific LLM Adaptation
by: Yang, Yuxin, et al.
Published: (2026)

Data Mixing for Large Language Models Pretraining: A Survey and Outlook
by: Chen, Zhuo, et al.
Published: (2026)

Task-Aware Calibration: Provably Optimal Decoding in LLMs
by: Tomov, Tim, et al.
Published: (2026)

Active Task Disambiguation with LLMs
by: Kobalczyk, Katarzyna, et al.
Published: (2025)

MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts
by: Guo, Haoqiang, et al.
Published: (2024)

Self-Pluralising Culture Alignment for Large Language Models
by: Xu, Shaoyang, et al.
Published: (2024)

HMS-BERT: Hybrid Multi-Task Self-Training for Multilingual and Multi-Label Cyberbullying Detection
by: Feng, Zixin, et al.
Published: (2026)

Unveiling the Influence of Amplifying Language-Specific Neurons
by: Rahmanisa, Inaya, et al.
Published: (2025)

Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning
by: Wang, Xiaolei, et al.
Published: (2024)

Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
by: Yang, Ziyu, et al.
Published: (2026)

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
by: Xiong, Zheyang, et al.
Published: (2024)

JNLP at SemEval-2025 Task 11: Cross-Lingual Multi-Label Emotion Detection Using Generative Models
by: Xue, Jieying, et al.
Published: (2025)

Optimizing Multi-Task Learning for Enhanced Performance in Large Language Models
by: Qi, Zhen, et al.
Published: (2024)

Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning
by: Aakanksha, et al.
Published: (2024)

Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text
by: Rao, Zixin, et al.
Published: (2025)

Whitening Not Recommended for Classification Tasks in LLMs
by: Forooghi, Ali, et al.
Published: (2024)

Spoken Language Understanding on Unseen Tasks With In-Context Learning
by: Agrawal, Neeraj, et al.
Published: (2025)

Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains
by: Xu, Austin, et al.
Published: (2025)

Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation
by: Nayak, Nihal V., et al.
Published: (2024)

Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning
by: Sarkar, Soumajyoti, et al.
Published: (2024)

Learning Task Representations from In-Context Learning
by: Saglam, Baturay, et al.
Published: (2025)

MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs
by: Yu, Xingtong, et al.
Published: (2023)

Quiet Feature Learning in Algorithmic Tasks
by: Naidu, Prudhviraj, et al.
Published: (2025)