paper-with-me

Papers

FactCheck: Feasibility-aware Long-term Action Anticipation with Multi-agent Collaboration

2026-06-10 · Rui Cao, Jiannong Cao, Bo Yuan, Zhiyuan Wen, Mingjin Zhang arxiv

Long-term action anticipation (LTA) aims to predict an ordered sequence of future verb-noun actions from a partially observed video. While this task serves as the foundation for embodied intelligence, anticipating physically feasible long-term actions remains a critical challenge. Existing methods, which operate in an open-loop manner, often hallucinate non-existent objects, violate object affordances, or disregard object states, as they lack explicit mechanisms to verify action feasibility against the physical environment. To address this, we propose FactCheck, a novel multi-agent collaboration framework that improves feasibility through a closed-loop "Observe-Plan-Verify" mechanism. FactCheck decomposes the complex LTA task into specialized roles: an Observer that recognizes historical actions from video observations and constructs a dual-form structured memory, comprising a History Action Abstract that captures high-level human intentions and environmental status, and a History Action Graph that encodes object states and temporal dependencies; a Planner that generates draft future actions conditioned on both low-level historical actions and high-level History Action Abstract; and a Verifier that rigorously validates the draft against the History Action Graph and refines infeasible actions. Extensive experiments on the EPIC-Kitchens-55 and EGTEA Gaze+ benchmarks demonstrate that FactCheck consistently outperforms state-of-the-art methods. Our work establishes a new paradigm for feasibility-aware long-term action anticipation, effectively closing the loop of action recognition, action prediction and action verification.

📄 PDF Abstract BibTeX arXiv:2606.14778

Code (0)

등록된 구현이 없습니다.

Tasks

Action AnticipationAction Recognition

Similar Papers 제목 키워드 기반

Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detection

2018-09-21 · Lev Konstantinovskiy, Oliver Price, Mevan Babakar, Arkaitz Zubiaga

In an effort to assist factcheckers in the process of factchecking, we tackle the claim detection task, one of the necessary stages prior to determining the veracity of a claim. It consists of identifying the set of sent…

Sentence

Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models

2026-04-15 · Dhruv Sahnan, Subhabrata Dutta, Tanmoy Chakraborty, Preslav Nakov 외 arxiv

Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reasoning models (LRMs) lack such grounding and primarily reason from availab…

Real-time Claim Detection from News Articles and Retrieval of Semantically-Similar Factchecks

2019-07-03 · Ben Adler, Giacomo Bosciani-Gilroy

Factchecking has always been a part of the journalistic process. However with newsroom budgets shrinking it is coming under increasing pressure just as the amount of false information circulating is on the rise. We there…

ArticlesRetrieval

FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs

2024-10-03 · Deema Alnuhait, Neeraja Kirtane, Muhammad Khalifa, Hao Peng

Language models (LMs) hallucinate. We inquire: Can we detect and mitigate hallucinations before they happen? This work answers this research question in the positive, by showing that the internal representations of LMs p…

Hallucination

OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs

2024-08-06 · Hasan Iqbal, Yuxia Wang, Minghan Wang, Georgi Georgiev 외

The increased use of large language models (LLMs) across a variety of real-world applications calls for automatic tools to check the factual accuracy of their outputs, as LLMs often hallucinate. This is difficult as it r…

Fact Checking