Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners
As Large Language Models (LLMs) achieve increasingly sophisticated performance on complex reasoning tasks, current architectures serve as critical proxies for the internal heuristics of frontier models. Characterizing emergent reasoning is vital for long-term interpretability and safety. Furthermore, understanding how prompting modulates these processes is essential, as natural language will likely be the primary interface for interacting with AGI systems. In this work, we use a custom variant of Genetic Pareto (GEPA) to systematically optimize prompts for scientific reasoning tasks, and analyze how prompting can affect reasoning behavior. We investigate the structural patterns and logical heuristics inherent in GEPA-optimized prompts, and evaluate their transferability and brittleness. Our findings reveal that gains in scientific reasoning often correspond to model-specific heuristics that fail to generalize across systems, which we call "local" logic. By framing prompt optimization as a tool for model interpretability, we argue that mapping these preferred reasoning structures for LLMs is an important prerequisite for effectively collaborating with superhuman intelligence.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Detecting (Un)answerability in Large Language Models with Linear Directions
Large language models (LLMs) often respond confidently to questions even when they lack the necessary information, leading to hallucinated answers. In this work, we study the problem of (un)answerability detection, focus…
Question AnsweringSafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
The success of large language models (LLMs) in scientific domains has heightened safety concerns, prompting numerous benchmarks to evaluate their scientific safety. Existing benchmarks often suffer from limited risk cove…
Genome-Bench: A Scientific Reasoning Benchmark from Real-World Expert Discussions
In this short report, we present an automated pipeline tailored for the genomics domain and introduce \textit{Genome-Bench}, a new benchmark constructed from over a decade of scientific forum discussions on genome engine…
Multiple-choiceThe Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates
With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The challenge is that base pre-trained models are optimized for next-to…
Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing
As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern. Existing deception monitors either score visible transcripts or derive scalar probe scores from represen…