conftrace_

attention head

146 papers

Explore in graph

Co-occurring keywords

attention mechanism (4001) large language model (13587) language model (4599) mechanistic interpretability (133) model compression (3302) transformer model (1996) in-context learning (1405) representation learning (6206) transformer architecture (1560) model pruning (237)

Papers

Mechanisms of Prompt-Induced Hallucination in Vision–Language Models ACL 2026

Query-Routed Activation Editing with Truth-hierarchical Preference Optimization AAAI 2026

CoFact: Dynamic Coordination of Attention Heads for Improving Factual Consistency in LLMs AAAI 2026

Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination ACL 2026

HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference ACL 2026

Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models AAAI 2026

What Matters to an LLM? Behavioral and Computational Evidences from Summarization EACL 2026

HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection AAAI 2026

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks AAAI 2026

Retrieval Heads are Dynamic ACL 2026

Mechanistic Analysis Of Universality: Numerical Comparison Circuits Across Transformer Architectures ACL 2026

The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces ACL 2026

Multi-component Causal Tracing in Large Language Models ACL 2026

Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract) AAAI 2026

Tug-of-war between idioms’ figurative and literal interpretations in LLMs EACL 2026

How Do LLMs Generate Contrastive Sentiments? A Mechanistic Perspective EACL 2026

Sycophancy Hides Linearly in the Attention Heads EACL 2026

A Robust Unlearning Method with Adaptive Knowledge Guidance and Memory Preservation AAAI 2026

Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification CONLL 2025

Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns ACL 2025

Structured Pruning for Diverse Best-of-N Reasoning Optimization ACL 2025

Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs ACL 2025

Language Models Grow Less Humanlike beyond Phase Transition ACL 2025

Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification ACL 2025

SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs ICCV 2025