paper-with-me

홈 › Papers

Prompting Large Language Models with Rationale Heuristics for Knowledge-based Visual Question Answering

2024-12-22 · Zhongjian Hu, Peng Yang, Bing Li, Fengyuan Liu

Recently, Large Language Models (LLMs) have been used for knowledge-based Visual Question Answering (VQA). Despite the encouraging results of previous studies, prior methods prompt LLMs to predict answers directly, neglecting intermediate thought processes. We argue that prior methods do not sufficiently activate the capacities of LLMs. We propose a framework called PLRH that Prompts LLMs with Rationale Heuristics for knowledge-based VQA. The PLRH prompts LLMs with Chain of Thought (CoT) to generate rationale heuristics, i.e., intermediate thought processes, and then leverages the rationale heuristics to inspire LLMs to predict answers. Experiments show that our approach outperforms the existing baselines by more than 2.2 and 2.1 on OK-VQA and A-OKVQA, respectively.

📄 PDF Abstract BibTeX arXiv:2412.16936

Code (0)

등록된 구현이 없습니다.

Tasks

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning

2023-01-12 · Zhenfang Chen, Qinhong Zhou, Yikang Shen, Yining Hong 외

Large pre-trained vision and language models have demonstrated remarkable capacities for various tasks. However, solving the knowledge-based visual reasoning tasks remains challenging, which requires a model to comprehen…

Few-Shot LearningImage CaptioningLanguage ModellingLarge Language Model+2

First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning

2024-06-23 · Yoichi Aoki, Keito Kudo, Tatsuki Kuribayashi, Shusaku Sone 외

Multi-step reasoning instruction, such as chain-of-thought prompting, is widely adopted to explore better language models (LMs) performance. We report on the systematic strategy that LMs employ in such a multi-step reaso…

Language ModelingLanguage Modelling

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

PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales

2022-11-03 · Peifeng Wang, Aaron Chan, Filip Ilievski, Muhao Chen 외

Neural language models (LMs) have achieved impressive results on various language-based reasoning tasks by utilizing latent knowledge encoded in their own pretrained parameters. To make this reasoning process more explic…

counterfactualDecision Making

Boosting Language Models Reasoning with Chain-of-Knowledge Prompting

2023-06-10 · Jianing Wang, Qiushi Sun, Xiang Li, Ming Gao

Recently, Chain-of-Thought (CoT) prompting has delivered success on complex reasoning tasks, which aims at designing a simple prompt like ``Let's think step by step'' or multiple in-context exemplars with well-designed r…

Arithmetic Reasoning