Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them
Large language models (LLMs) and Vision language models (VLMs) have been able to perform various forms of reasoning tasks in a wide range of scenarios, but are they truly engaging in task abstraction and rule-based reasoning beyond mere memorization and pattern matching? To answer this question, we propose a novel experimental approach, Misleading Fine-Tuning (MisFT), to examine whether LLMs/VLMs perform abstract reasoning by altering their original understanding of fundamental rules. In particular, by constructing a dataset with math expressions that contradict correct operation principles, we fine-tune the model to learn those contradictory rules and assess its generalization ability on different test domains. Through a series of experiments, we find that current LLMs/VLMs are capable of effectively applying contradictory rules to solve practical math word problems and math expressions represented by images, implying the presence of an internal mechanism that abstracts before reasoning.
Code (0)
등록된 구현이 없습니다.
Tasks
MathMemorizationSimilar Papers 제목 키워드 기반
Efficient Reasoning with Hidden Thinking
Chain-of-Thought (CoT) reasoning has become a powerful framework for improving complex problem-solving capabilities in Multimodal Large Language Models (MLLMs). However, the verbose nature of textual reasoning introduces…
DecoderMultimodal ReasoningPhysics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
Recent advances in language models have demonstrated their capability to solve mathematical reasoning problems, achieving near-perfect accuracy on grade-school level math benchmarks like GSM8K. In this paper, we formally…
GSM8KMathMathematical ReasoningUnderstanding Hidden Computations in Chain-of-Thought Reasoning
Chain-of-Thought (CoT) prompting has significantly enhanced the reasoning abilities of large language models. However, recent studies have shown that models can still perform complex reasoning tasks even when the CoT is …
Language ModelingLanguage ModellingSelfIE: Self-Interpretation of Large Language Model Embeddings
How do large language models (LLMs) obtain their answers? The ability to explain and control an LLM's reasoning process is key for reliability, transparency, and future model developments. We propose SelfIE (Self-Interpr…
Language ModelingLanguage ModellingLarge Language ModelmodelLarge Language Models are Zero-Shot Reasoners
Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specific exemplars. Notably, chain of thought (…
Arithmetic ReasoningCommon Sense ReasoningDate UnderstandingFew-Shot Learning+3