paper-with-me

Papers

Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models

2024-03-26 · Zhenyu Pan, Haozheng Luo, Manling Li, Han Liu

We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA). Compared to the literature, CoA overcomes two major challenges of current QA applications: (i) unfaithful hallucination that is inconsistent with real-time or domain facts and (ii) weak reasoning performance over compositional information. Our key contribution is a novel reasoning-retrieval mechanism that decomposes a complex question into a reasoning chain via systematic prompting and pre-designed actions. Methodologically, we propose three types of domain-adaptable `Plug-and-Play' actions for retrieving real-time information from heterogeneous sources. We also propose a multi-reference faith score (MRFS) to verify and resolve conflicts in the answers. Empirically, we exploit both public benchmarks and a Web3 case study to demonstrate the capability of CoA over other methods.

📄 PDF Abstract BibTeX arXiv:2403.17359

Code (1)

MAGICS-LAB/Chain-of-Actions 공식 구현 pytorch

Tasks

HallucinationInformation RetrievalQuestion AnsweringRetrieval

Similar Papers 제목 키워드 기반

Measuring Faithfulness in Chain-of-Thought Reasoning

2023-07-17 · Tamera Lanham, Anna Chen, Ansh Radhakrishnan, Benoit Steiner 외

Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasoning is a faithful explanation of the model…

Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning

2023-11-07 · Ruosen Li, Xinya Du

Neural models, including large language models (LLMs), achieve superior performance on multi-hop question-answering. To elicit reasoning capabilities from LLMs, recent works propose using the chain-of-thought (CoT) mecha…

Multi-hop Question AnsweringQuestion Answering

Faithful Chain-of-Thought Reasoning

2023-01-31 · Qing Lyu, Shreya Havaldar, Adam Stein, Li Zhang 외

While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. …

MathMulti-hop Question AnsweringQuestion Answering

Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning

2022-10-21 · Oyvind Tafjord, Bhavana Dalvi Mishra, Peter Clark

Our goal is a question-answering (QA) system that can show how its answers are implied by its own internal beliefs via a systematic chain of reasoning. Such a capability would allow better understanding of why a model pr…

Question Answering

Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs

2025-11-11 · Junxian Li, Xinyue Xu, Sai Ma, Di Zhang 외 arxiv

Multimodal Large Language Models (MLLMs) frequently suffer from unfaithfulness, generating reasoning chains that drift from visual evidence or contradict final predictions. We propose Faithful-First Reasoning, Planning, …

Multimodal Reasoning