Imagen de Portada

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chowdhary, Pratim, Chin, Peter, Chakrabarty, Deepernab
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AssertBench: A Benchmark for Evaluating Self-Assertion in Large Language Models
por: Lee, Jaeho, et al.
Publicado: (2025)

Necessary and Sufficient Watermark for Large Language Models
por: Takezawa, Yuki, et al.
Publicado: (2023)

Latent Performance Profiling of Large Language Models
por: Chakraborty, Tanmoy, et al.
Publicado: (2026)

Unmasking Hallucinations: A Causal Graph-Attention Perspective on Factual Reliability in Large Language Models
por: kurra, Sailesh kiran, et al.
Publicado: (2026)

SAP: Syntactic Attention Pruning for Transformer-based Language Models
por: Lee, Tzu-Yun, et al.
Publicado: (2025)

Circuit Component Reuse Across Tasks in Transformer Language Models
por: Merullo, Jack, et al.
Publicado: (2023)

Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo
por: Loula, João, et al.
Publicado: (2025)

Paraphrase and Aggregate with Large Language Models for Minimizing Intent Classification Errors
por: Yadav, Vikas, et al.
Publicado: (2024)

Syntactic Control of Language Models by Posterior Inference
por: Xefteri, Vicky, et al.
Publicado: (2025)

Evaluating Large Language Models for Public Health Classification and Extraction Tasks
por: Harris, Joshua, et al.
Publicado: (2024)

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
por: Kazemi, Hamid, et al.
Publicado: (2026)

LOLgorithm: Integrating Semantic,Syntactic and Contextual Elements for Humor Classification
por: Khurana, Tanisha, et al.
Publicado: (2024)

Adaptive Task Vectors for Large Language Models
por: Kang, Joonseong, et al.
Publicado: (2025)

Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models
por: Das, Anindya Sundar, et al.
Publicado: (2025)

Benchmarking Large Language Models for Math Reasoning Tasks
por: Seßler, Kathrin, et al.
Publicado: (2024)

Leveraging Large Language Models and Topic Modeling for Toxicity Classification
por: Oskouie, Haniyeh Ehsani, et al.
Publicado: (2024)

Scaling Laws for Discriminative Classification in Large Language Models
por: Wyatte, Dean, et al.
Publicado: (2024)

Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models
por: Dumpala, Sri Harsha, et al.
Publicado: (2024)

Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization
por: Shin, Sungbin, et al.
Publicado: (2024)

Frustratingly Easy Task-aware Pruning for Large Language Models
por: Tian, Yuanhe, et al.
Publicado: (2025)

Scaling Laws for Downstream Task Performance of Large Language Models
por: Isik, Berivan, et al.
Publicado: (2024)

Experimental Design for Active Transductive Inference in Large Language Models
por: Mukherjee, Subhojyoti, et al.
Publicado: (2024)

Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models
por: Cao, Jinghan, et al.
Publicado: (2026)

Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks
por: Lin, Fangru, et al.
Publicado: (2024)

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

Local Prompt Optimization
por: Jain, Yash, et al.
Publicado: (2025)

Evaluating Large Language Models for Health-Related Text Classification Tasks with Public Social Media Data
por: Guo, Yuting, et al.
Publicado: (2024)

Revisiting In-context Learning Inference Circuit in Large Language Models
por: Cho, Hakaze, et al.
Publicado: (2024)

Interpretable Syntactic Representations Enable Hierarchical Word Vectors
por: Silwal, Biraj
Publicado: (2024)

Large Language Models For Text Classification: Case Study And Comprehensive Review
por: Kostina, Arina, et al.
Publicado: (2025)

Hierarchical Text Classification Using Black Box Large Language Models
por: Yoshimura, Kosuke, et al.
Publicado: (2025)

Unmask It! AI-Generated Product Review Detection in Dravidian Languages
por: De, Somsubhra, et al.
Publicado: (2025)

Cross-Lingual Empirical Evaluation of Large Language Models for Arabic Medical Tasks
por: Abouzahir, Chaimae, et al.
Publicado: (2026)

Dynamic Rank Reinforcement Learning for Adaptive Low-Rank Multi-Head Self Attention in Large Language Models
por: Erden, Caner
Publicado: (2025)

Enhancing Granular Sentiment Classification with Chain-of-Thought Prompting in Large Language Models
por: Miriyala, Vihaan, et al.
Publicado: (2025)

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
por: Zhu, Zhaowei, et al.
Publicado: (2023)

Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer
por: Dong, Yihe, et al.
Publicado: (2025)

LemmaHead: RAG Assisted Proof Generation Using Large Language Models
por: Yang, Tianbo, et al.
Publicado: (2025)

Fourier Head: Helping Large Language Models Learn Complex Probability Distributions
por: Gillman, Nate, et al.
Publicado: (2024)

AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation
por: Chakrabarty, Tuhin, et al.
Publicado: (2025)