paper-with-me

홈 › Papers

Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them

2025-03-20 · GuanYu Chen, Peiyang Wang, Tianren Zhang, Feng Chen

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.

📄 PDF Abstract BibTeX arXiv:2503.16401

Code (0)

등록된 구현이 없습니다.

Tasks

MathMemorization

Similar Papers 제목 키워드 기반

Efficient Reasoning with Hidden Thinking

2025-01-31 · Xuan Shen, Yizhou Wang, Xiangxi Shi, Yanzhi Wang 외

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 Reasoning

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

2024-07-29 · Tian Ye, Zicheng Xu, Yuanzhi Li, Zeyuan Allen-Zhu

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 Reasoning

Understanding Hidden Computations in Chain-of-Thought Reasoning

2024-12-05 · Aryasomayajula Ram Bharadwaj

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 Modelling

SelfIE: Self-Interpretation of Large Language Model Embeddings

2024-03-16 · Haozhe Chen, Carl Vondrick, Chengzhi Mao

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 Modelmodel

Large Language Models are Zero-Shot Reasoners

2022-05-24 · Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo 외

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