paper-with-me

홈 › Papers

System-Level Natural Language Feedback

2023-06-23 · Weizhe Yuan, Kyunghyun Cho, Jason Weston

Natural language (NL) feedback offers rich insights into user experience. While existing studies focus on an instance-level approach, where feedback is used to refine specific examples, we introduce a framework for system-level use of NL feedback. We show how to use feedback to formalize system-level design decisions in a human-in-the-loop-process -- in order to produce better models. In particular this is done through: (i) metric design for tasks; and (ii) language model prompt design for refining model responses. We conduct two case studies of this approach for improving search query and dialog response generation, demonstrating the effectiveness of system-level feedback. We show the combination of system-level and instance-level feedback brings further gains, and that human written instance-level feedback results in more grounded refinements than GPT-3.5 written ones, underlying the importance of human feedback for building systems. We release our code and data at https://github.com/yyy-Apple/Sys-NL-Feedback.

📄 PDF Abstract BibTeX arXiv:2306.13588

Code (1)

yyy-apple/sys-nl-feedback 공식 구현

Tasks

Language ModelingLanguage ModellingResponse Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음
Weight Decay 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback

2020-05-05 · ACL 2020 6 · Ahmed Elgohary, Saghar Hosseini, Ahmed Hassan Awadallah

We study the task of semantic parse correction with natural language feedback. Given a natural language utterance, most semantic parsing systems pose the problem as one-shot translation where the utterance is mapped to a…

FormSemantic ParsingText to SQLText-To-SQL+1

RL with Learnable Textual Feedback: A Bilevel Approach

2026-05-23 · Utsav Singh, Sidhaarth Sredharan, Souradip Chakraborty, Amrit Singh Bedi arxiv

Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This has motivated a growing line of work on RL with textual feedback, w…

Reinforcement Learning

EditScribe: Non-Visual Image Editing with Natural Language Verification Loops

2024-08-13 · Ruei-Che Chang, Yuxuan Liu, Lotus Zhang, Anhong Guo

Image editing is an iterative process that requires precise visual evaluation and manipulation for the output to match the editing intent. However, current image editing tools do not provide accessible interaction nor su…

Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning

2026-03-04 · Lei Huang, Xiang Cheng, Chenxiao Zhao, Guobin Shen 외 arxiv

Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorithms rely solely on scalar rewards, leavi…

Reinforcement Learning

A Deep Reinforcement Learning Approach for Interactive Search with Sentence-level Feedback

2023-10-03 · Jianghong Zhou, Joyce C. Ho, Chen Lin, Eugene Agichtein

Interactive search can provide a better experience by incorporating interaction feedback from the users. This can significantly improve search accuracy as it helps avoid irrelevant information and captures the users' sea…

Deep Reinforcement LearningQ-LearningReinforcement Learning (RL)Sentence