REVIEW 7 cited by
Attention Heads of Large Language Models: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various tasks but remain as black-box systems. Understanding the reasoning bottlenecks of LLMs has become a critical challenge, as these limitations are deeply tied to their internal architecture. Among these, attention heads have emerged as a focal point for investigating the underlying mechanics of LLMs. In this survey, we aim to demystify the internal reasoning processes of LLMs by systematically exploring the roles and mechanisms of attention heads. We first introduce a novel four-stage framework inspired by the human thought process: Knowledge Recalling, In-Context Identification, Latent Reasoning, and Expression Preparation. Using this framework, we comprehensively review existing research to identify and categorize the functions of specific attention heads. Additionally, we analyze the experimental methodologies used to discover these special heads, dividing them into two categories: Modeling-Free and Modeling-Required methods. We further summarize relevant evaluation methods and benchmarks. Finally, we discuss the limitations of current research and propose several potential future directions.
Forward citations
Cited by 7 Pith papers
-
How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair
LLM program-repair success is associated with diffuse attention across diagnostic bug-report content, while failures correlate with over-focus on metadata such as version information.
-
Steering at the Source: Style Modulation Heads for Robust Persona Control
Steering only three 'Style Modulation Heads' controls personas with less coherency collapse than residual-stream steering, across six personas and two base LLMs.
-
Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
LLM attention maps reveal a preplan-and-anchor pattern, and reweighting RL credit toward the flagged tokens improves math/QA reasoning.
-
CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation
A method that uses a handful of 'semantic retrieval heads' instead of all attention heads to decide which key-value cache entries can be dropped, plus layer-wise cache budgeting, reportedly beats prior KV compression ...
-
Safety Alignment Should Be Made More Than Just A Few Attention Heads
Safety-critical attention heads are few, jailbreak prompts lower their refusal-direction signal, and fine-tuning with head-level dropout spreads safety and improves robustness.
-
ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models
ALPS selects task-sensitive attention heads by measuring Wasserstein distance between base and task-tuned weights, and freezing other heads during fine-tuning improves performance and efficiency.
-
Graph-of-Causal Evolution: Challenging Chain-of-Model for Reasoning
GoCE swaps CoM's chain structure for a differentiable causal graph and reports accuracy gains on CLUTRR, CLadder, EX-FEVER, and CausalQA, but the evidence is sandbox-generated and unauditable.
Discussion (0). Sign in to comment.