paper-with-me

Papers

Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos

2024-09-30 · Md Mohaiminul Islam, Tushar Nagarajan, Huiyu Wang, Fu-Jen Chu, Kris Kitani, Gedas Bertasius, Xitong Yang

Goal-oriented planning, or anticipating a series of actions that transition an agent from its current state to a predefined objective, is crucial for developing intelligent assistants aiding users in daily procedural tasks. The problem presents significant challenges due to the need for comprehensive knowledge of temporal and hierarchical task structures, as well as strong capabilities in reasoning and planning. To achieve this, prior work typically relies on extensive training on the target dataset, which often results in significant dataset bias and a lack of generalization to unseen tasks. In this work, we introduce VidAssist, an integrated framework designed for zero/few-shot goal-oriented planning in instructional videos. VidAssist leverages large language models (LLMs) as both the knowledge base and the assessment tool for generating and evaluating action plans, thus overcoming the challenges of acquiring procedural knowledge from small-scale, low-diversity datasets. Moreover, VidAssist employs a breadth-first search algorithm for optimal plan generation, in which a composite of value functions designed for goal-oriented planning is utilized to assess the predicted actions at each step. Extensive experiments demonstrate that VidAssist offers a unified framework for different goal-oriented planning setups, e.g., visual planning for assistance (VPA) and procedural planning (PP), and achieves remarkable performance in zero-shot and few-shot setups. Specifically, our few-shot model outperforms the prior fully supervised state-of-the-art method by +7.7% in VPA and +4.81% PP task on the COIN dataset while predicting 4 future actions. Code, and models are publicly available at https://sites.google.com/view/vidassist.

📄 PDF Abstract BibTeX arXiv:2409.20557

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Fairness of ChatGPT and the Role Of Explainable-Guided Prompts

2023-07-14 · Yashar Deldjoo

Our research investigates the potential of Large-scale Language Models (LLMs), specifically OpenAI's GPT, in credit risk assessment-a binary classification task. Our findings suggest that LLMs, when directed by judicious…

Binary ClassificationFairness

A Survey on Large Language Model Hallucination via a Creativity Perspective

2024-02-02 · Xuhui Jiang, Yuxing Tian, Fengrui Hua, Chengjin Xu 외

Hallucinations in large language models (LLMs) are always seen as limitations. However, could they also be a source of creativity? This survey explores this possibility, suggesting that hallucinations may contribute to L…

HallucinationLanguage ModelingLanguage ModellingLarge Language Model+1

Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas

2024-10-18 · Xiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang 외

Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery. However, existing LLMs often produce simplistic and repetitive suggestions …

Diversity

Harnessing the power of LLMs for normative reasoning in MASs

2024-03-25 · Bastin Tony Roy Savarimuthu, Surangika Ranathunga, Stephen Cranefield

Software agents, both human and computational, do not exist in isolation and often need to collaborate or coordinate with others to achieve their goals. In human society, social mechanisms such as norms ensure efficient …

Decision Making

Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in Large Language Models

2025-08-04 · Soyeon Kim, Jindong Wang, Xing Xie, Steven Euijong Whang arxiv

Facts change over time, making it essential for Large Language Models (LLMs) to handle time-sensitive factual knowledge accurately and reliably. Although factual Time-Sensitive Question-Answering (TSQA) tasks have been w…