Shared Lexical Task Representations Explain Behavioral Variability In LLMs

2026-04-23

AI Summary

This study addresses the instability of large language models (LLMs) across different prompting styles, a phenomenon whose underlying mechanisms remain poorly understood. By systematically comparing instruction-based and exemplar-based prompts through attention head analysis, representational probing, and behavioral experiments, the work identifies for the first time a shared “lexical task attention head” that operates consistently across prompting paradigms. The activation strength of this attention head strongly correlates with model performance and reliably triggers task-relevant answer generation. Furthermore, the research reveals that competition among internal task representations is a key driver of prompt sensitivity. These findings offer an interpretable framework for understanding LLM internal dynamics and suggest novel directions for enhancing prompt robustness.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Large Vision Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the question is posed. We investigate this variation by comparing two very different but commonly-used styles of prompting: instruction-based prompts, which describe the task in natural language, and example-based prompts, which provide in-context few-shot demonstration pairs to illustrate the task. We find that, despite large variation in performance as a function of the prompt, the model engages some common underlying mechanisms across different prompts of a task. Specifically, we identify task-specific attention heads whose outputs literally describe the task -- which we dub lexical task heads -- and show that these heads are shared across prompting styles and trigger subsequent answer production. We further find that behavioral variation between prompts can be explained by the degree to which these heads are activated, and that failures are at least sometimes due to competing task representations that dilute the signal of the target task. Our results together present an increasingly clear picture of how LLMs' internal representations can explain behavior that otherwise seems idiosyncratic to users and developers.

Problem

• prompt sensitivity
• behavioral variability
• large language models
• task representation
• lexical task heads

Innovation

• lexical task heads
• prompt sensitivity
• attention mechanisms
• task representation
• in-context learning