paper-with-me

홈 › Papers

Give me a hint: Can LLMs take a hint to solve math problems?

2024-10-08 · Vansh Agrawal, Pratham Singla, Amitoj Singh Miglani, Shivank Garg, Ayush Mangal

While state-of-the-art LLMs have shown poor logical and basic mathematical reasoning, recent works try to improve their problem-solving abilities using prompting techniques. We propose giving "hints" to improve the language model's performance on advanced mathematical problems, taking inspiration from how humans approach math pedagogically. We also test robustness to adversarial hints and demonstrate their sensitivity to them. We demonstrate the effectiveness of our approach by evaluating various diverse LLMs, presenting them with a broad set of problems of different difficulties and topics from the MATH dataset and comparing against techniques such as one-shot, few-shot, and chain of thought prompting.

📄 PDF Abstract BibTeX arXiv:2410.05915

Code (1)

vlgiitr/llm-math 공식 구현 pytorch

Tasks

Adversarial RobustnessMathMathematical ReasoningSensitivity

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Designing and Evaluating Chain-of-Hints for Scientific Question Answering

2025-10-24 · Anubhav Jangra, Smaranda Muresan arxiv

LLMs are reshaping education, with students increasingly relying on them for learning. Implemented using general-purpose models, these systems are likely to give away the answers, potentially undermining conceptual under…

Question Answering

WikiHint: A Human-Annotated Dataset for Hint Ranking and Generation

2024-12-02 · Jamshid Mozafari, Florian Gerhold, Adam Jatowt

The use of Large Language Models (LLMs) has increased significantly with users frequently asking questions to chatbots. In the time when information is readily accessible, it is crucial to stimulate and preserve human co…

DecoderHint Generation

Can Language Models Take A Hint? Prompting for Controllable Contextualized Commonsense Inference

2024-10-03 · Pedro Colon-Hernandez, Nanxi Liu, Chelsea Joe, Peter Chin 외

Generating commonsense assertions within a given story context remains a difficult task for modern language models. Previous research has addressed this problem by aligning commonsense inferences with stories and trainin…

Data AugmentationText Generation

Unspoken Hints: Accuracy Without Acknowledgement in LLM Reasoning

2025-09-30 · Arash Marioriyad, Shaygan Adim, Nima Alighardashi, Mahdieh Soleymani Banghshah 외 arxiv

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) prompting to solve mathematical and logical reasoning tasks. Yet, a central question remains: to what extent are these generated rationales \emph{f…

Logical Reasoning

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason

2025-07-03 · Kaiyi Zhang, Ang Lv, Jinpeng Li, Yongbo Wang 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving the complex reasoning abilities of large language models (LLMs). However, current RLVR methods face two significant challenges: …

Reinforcement Learning