paper-with-me

Papers

Continually Improving Extractive QA via Human Feedback

2023-05-21 · Ge Gao, Hung-Ting Chen, Yoav Artzi, Eunsol Choi

We study continually improving an extractive question answering (QA) system via human user feedback. We design and deploy an iterative approach, where information-seeking users ask questions, receive model-predicted answers, and provide feedback. We conduct experiments involving thousands of user interactions under diverse setups to broaden the understanding of learning from feedback over time. Our experiments show effective improvement from user feedback of extractive QA models over time across different data regimes, including significant potential for domain adaptation.

📄 PDF Abstract BibTeX arXiv:2305.12473

Code (1)

lil-lab/qa-from-hf 공식 구현 pytorch

Tasks

Domain AdaptationExtractive Question-AnsweringQuestion Answering

Similar Papers 제목 키워드 기반

Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs

2024-07-05 · Mihir Parmar, Hanieh Deilamsalehy, Franck Dernoncourt, Seunghyun Yoon 외

Extractive summarization plays a pivotal role in natural language processing due to its wide-range applications in summarizing diverse content efficiently, while also being faithful to the original content. Despite signi…

Extractive Summarization

Simulating Bandit Learning from User Feedback for Extractive Question Answering

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning …

Extractive Question-AnsweringQuestion Answering

Simulating Bandit Learning from User Feedback for Extractive Question Answering

2022-03-18 · ACL 2022 5 · Ge Gao, Eunsol Choi, Yoav Artzi

We study learning from user feedback for extractive question answering by simulating feedback using supervised data. We cast the problem as contextual bandit learning, and analyze the characteristics of several learning …

Extractive Question-AnsweringQuestion Answering

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 lan…

Continual LearningInstruction Following

Continual Learning with Delayed Feedback

2019-09-25 · THEIVENDIRAM PRANAVAN, Terence Sim

Most of the artificial neural networks are using the benefit of labeled datasets whereas in human brain, the learning is often unsupervised. The feedback or a label for a given input or a sensory stimuli is not often ava…

Continual Learning