paper-with-me

Papers

Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning

2026-02-08 · Po-Chun Chen, Hen-Hsen Huang, Hsin-Hsi Chen arxiv

To address the instability of unguided reasoning paths in standard Chain-of-Thought prompting, recent methods guide large language models (LLMs) by first eliciting a single reasoning strategy. However, relying on just one strategy for each question can still limit performance across diverse tasks. We propose Diverge-to-Induce Prompting (DIP), a framework that first prompts an LLM to generate multiple diverse high-level rationales for each question. Each rationale is then elaborated into a detailed, step-by-step draft plan. Finally, these draft plans are induced into a final plan. DIP enhances zero-shot reasoning accuracy without reliance on resource-intensive sampling. Experiments show that DIP outperforms single-strategy prompting, demonstrating the effectiveness of multi-plan induction for prompt-based reasoning.

📄 PDF Abstract BibTeX arXiv:2602.08028

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models

2024-07-14 · Yuchen Yang, Kwonjoon Lee, Behzad Dariush, Yinzhi Cao 외

Video Anomaly Detection (VAD) is crucial for applications such as security surveillance and autonomous driving. However, existing VAD methods provide little rationale behind detection, hindering public trust in real-worl…

Anomaly DetectionVideo Anomaly Detection

Rationale-Augmented Ensembles in Language Models

2022-07-02 · Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le 외

Recent research has shown that rationales, or step-by-step chains of thought, can be used to improve performance in multi-step reasoning tasks. We reconsider rationale-augmented prompting for few-shot in-context learning…

In-Context LearningPrompt EngineeringQuestion AnsweringSentiment Analysis+1

Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models

2024-05-22 · Qiji Zhou, Ruochen Zhou, Zike Hu, Panzhong Lu 외

Recent advancements in Chain-of-Thought (CoT) and related rationale-based works have significantly improved the performance of Large Language Models (LLMs) in complex reasoning tasks. With the evolution of Multimodal Lar…

Multimodal ReasoningVisual Question AnsweringVisual Reasoning

Stablizing Adversarial Invariance Induction by Discriminator Matching

2019-09-25 · Yusuke Iwasawa, Kei Akuzawa, Yutaka Matsuo

Incorporating the desired invariance into representation learning is a key challenge in many situations, e.g., for domain generalization and privacy/fairness constraints. An adversarial invariance induction (AII) shows i…

AttributeDomain GeneralizationFairnessRepresentation Learning

MCC-KD: Multi-CoT Consistent Knowledge Distillation

2023-10-23 · Hongzhan Chen, Siyue Wu, Xiaojun Quan, Rui Wang 외

Large language models (LLMs) have showcased remarkable capabilities in complex reasoning through chain of thought (CoT) prompting. Recently, there has been a growing interest in transferring these reasoning abilities fro…

DiversityKnowledge DistillationMathematical Reasoning