arXiv AI
Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
6d ago
Prompt Minimization: Reducing Input Redundancy Without Sacrificing Output Fidelity
The paper investigates prompt minimization, aiming to reduce prompts to their smallest, most information-dense form without losing output fidelity. It argues that shorter prompts lower computational overhead and inference latency, especially when large contexts are unnecessarily included, and that longer prompts can harm LLM reasoning and accuracy. The authors propose three frameworks to identify minimal prompts and show that these often produce outputs comparable to longer versions, highlighting redundancy in the input space and opening new avenues for efficient prompt engineering.
arXiv AI
Jul 1
Shared Lexical Task Representations Explain Behavioral Variability In LLMs
arXiv:2604. 22027v2 Announce Type: replace-cross 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.
arXiv AI
Jun 9
Cross-LLM Consistency in Inference: Evidence from Shared Interactions
arXiv:2606. 08129v1 Announce Type: new Abstract: Large language models (LLMs) differ in architecture, training data, and optimization procedures, yet they may still develop similar internal inference patterns.
arXiv Machine Learning
Sep 22
Evaluation Awareness Shifts from Format to Context with Model Scale
arXiv:2609.22119v1 Announce Type: cross Abstract: Evaluation awareness poses an unprecedented threat to model evaluation, but the mechanisms by which models detect it remain unknown. This study focus...
arXiv Computation and Language
Aug 31
Learning a Single Token to Replace Long System Prompts in LLMs
arXiv:2511.23271v2 Announce Type: replace Abstract: Long system prompts are widely used to steer Large Language Models (LLMs), but repeatedly processing them at inference time is inefficient and cons...
arXiv AI
Jul 1
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
arXiv:2606. 32038v1 Announce Type: cross Abstract: When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, rather than superficial imitation?