paper-with-me

홈 › Papers

Continual Learning for Instruction Following from Realtime Feedback

2022-12-19 · NeurIPS 2023 11 · Alane Suhr, Yoav Artzi

We propose and deploy an approach to continually train an instruction-following agent from feedback provided by users during collaborative interactions. During interaction, human users instruct an agent using natural language, and provide realtime binary feedback as they observe the agent following their instructions. We design a contextual bandit learning approach, converting user feedback to immediate reward. We evaluate through thousands of human-agent interactions, demonstrating 15.4% absolute improvement in instruction execution accuracy over time. We also show our approach is robust to several design variations, and that the feedback signal is roughly equivalent to the learning signal of supervised demonstration data.

📄 PDF Abstract BibTeX arXiv:2212.09710

Code (1)

lil-lab/clif_cb 공식 구현 pytorch

Tasks

Continual LearningInstruction Following

Similar Papers 제목 키워드 기반

InstructionCP: A fast approach to transfer Large Language Models into target language

2024-05-30 · Kuang-Ming Chen, Hung-Yi Lee

The rapid development of large language models (LLMs) in recent years has largely focused on English, resulting in models that respond exclusively in English. To adapt these models to other languages, continual pre-train…

Instruction Following

Separable Mixture of Low-Rank Adaptation for Continual Visual Instruction Tuning

2024-11-21 · Ziqi Wang, Chang Che, Qi Wang, Yangyang Li 외

Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instr…

Continual LearningInstruction Following

Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following

2025-09-10 · Minjong Yoo, Jinwoo Jang, Wei-jin Park, Honguk Woo arxiv

This study presents an Exploratory Retrieval-Augmented Planning (ExRAP) framework, designed to tackle continual instruction following tasks of embodied agents in dynamic, non-stationary environments. The framework enhanc…

Instruction Following

Continual Instruction Tuning for Large Multimodal Models

2023-11-27 · Jinghan He, Haiyun Guo, Ming Tang, Jinqiao Wang

Instruction tuning is now a widely adopted approach to aligning large multimodal models (LMMs) to follow human intent. It unifies the data format of vision-language tasks, enabling multi-task joint training. However, vis…

Continual Learning

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

2024-06-19 · Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia 외

One core capability of large language models (LLMs) is to follow natural language instructions. However, the issue of automatically constructing high-quality training data to enhance the complex instruction-following abi…

Instruction Following