Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues
Not on the map. Why?
Abstract (arXiv)
Implicit user feedback, user emotions and demographic information have shown to be promising sources for improving the accuracy and user engagement of responses generated by dialogue systems. However, the influence of such information on task completion and factual consistency, which are important criteria for task-oriented and document-grounded dialogues, is not yet known. To address this, we introduce FEDI, the first English task-oriented and document-grounded dialogue dataset annotated with this information. Our experiments with Flan-T5, GPT-2 and Llama 2 show a particularly positive impact on task completion and factual consistency. Participants in our human evaluation reported that the responses generated by the feedback-trained models were more informative (Flan-T5 and GPT-2), relevant and factual consistent (Llama 2).
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 29 of its 54 references that are in the map. First posted on arXiv 17 Jan 2024.
Builds on
29 of 54 references.
References · 29
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
- 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
- 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
- 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 204
- 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 201
- 2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 166
- 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 131
- 2021On Releasing Annotator-Level Labels and Information in Datasetscited by 123
- 2019Learning from Dialogue after Deployment: Feed Yourself, Chatbot!cited by 102
17 more
- 2023Aligning Language Models to User Opinionscited by 98
- 2018EmotionLines: An Emotion Corpus of Multi-Party Conversationscited by 80
- 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
- 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
- 2022Don't Blame the Annotator: Bias Already Starts in the Annotation Instructionscited by 47
- 2020DoQA -- Accessing Domain-Specific FAQs via Conversational QAcited by 42
- 2023SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Promptingcited by 39
- 2021SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failurescited by 37
- 2022Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedbackcited by 35
- 2023NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violationcited by 24
- 2019Incremental Learning from Scratch for Task-Oriented Dialogue Systemscited by 11
- 2023Improving Open Language Models by Learning from Organic Interactionscited by 10
- 2023Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Functioncited by 7
- 2023Self-Supervised Prediction of the Intention to Interact with a Service Robotcited by 7
- 2023Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?cited by 7
- 2023Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialoguescited by 5
- 2021Evaluate On-the-job Learning Dialogue Systems and a Case Study for Natural Language Understandingcited by 2
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.