Challenge: Errors in general chatbots and chatbot that follow a rough persona have been studied . but those in chatbot based on real people have not been thoroughly investigated .
Approach: They analyze dialogue data of a generation-based chatbot trained from dialogue data . they find errors in attributes and relations can be divided into two levels: self and other .
Outcome: The results show that errors in chatbots can be divided into two types . the correspondence with an existing taxonomy of errors was also investigated .

Similar Papers

Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Large Language Models enable them to follow freeform instructions, including imitating generic or specific demographic personas in conversations.
Approach: They propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a model that incorporates both generic and specific personas.
Outcome: The proposed model systematically measures persona biases in harmful expression and harmful agreement.
Exploring the Impact of Human Evaluator Group on Chat-Oriented Dialogue Evaluation (2024.lrec-main)

Copied to clipboard

Challenge: Evaluator groups such as domain experts, university students, and crowdworkers have been used to assess and compare chat-oriented dialogue systems.
Approach: They analyze the impact of evaluator groups on dialogue system evaluation by testing 4 state-of-the-art dialogue systems using 4 distinct evaluer groups.
Outcome: The proposed evaluations show that the evaluator group impact is not seen for Pairwise, and that it is beneficial for certain metrics.
A Typology of Errors for User Utterances in Chatbots (2024.lrec-main)

Copied to clipboard

Challenge: Non-prescriptive language uses in chatbot communication create challenges for Semantic Parsing (SP).
Approach: They propose a typology based on a sample of non-prescriptive language uses mined from a domain-specific chatbot log and a framework for automatically mapping these errors to the typology.
Outcome: The proposed typology can be extended to include new classes of errors across different domains and user demographics.
The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity (2021.acl-long)

Copied to clipboard

Challenge: We analyze 2,500 phrasings related to the intent of “Are you a robot?” and 2,500 adversarially selected utterances to determine whether systems are non-human.
Approach: They analyze 2,500 phrasings related to the intent of "Are you a robot?" and 2,500 adversarially selected utterances to determine whether systems are non-human.
Outcome: The proposed model and two systems fail to confirm non-human intent, and the proposed model is complex.
Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations (2024.lrec-main)

Copied to clipboard

Challenge: Personalization is a multifaceted process that requires multiple definitions and varies between individuals.
Approach: They propose to systemically survey the recent landscape of personalized dialogue generation including the datasets employed, methodologies developed, and evaluation metrics applied.
Outcome: The proposed model can generate fluent and coherent responses to human queries in a language-based conversational agent.
Inconsistent dialogue responses and how to recover from them (2024.findings-eacl)

Copied to clipboard

Challenge: Existing methods to assess and bolster utterance consistency of chat systems have been shown difficult to detect.
Approach: They propose to use annotators to write dialogue responses and recovery utterances to assess and bolster utteration consistency of chat systems.
Outcome: The proposed dataset significantly improves the detection and resolution of inconsistencies in chat conversations.
Training Millions of Personalized Dialogue Agents (D18-1)

Copied to clipboard

Challenge: Current dialogue systems fail at being engaging for users when trained end-to-end without relying on proactive reengaging scripted strategies.
Approach: They propose a dataset that provides 5 million personas and 700 million person-based dialogues.
Outcome: The proposed dataset provides 5 million personas and 700 million person-based dialogues.
Getting To Know You: User Attribute Extraction from Dialogues (2020.lrec-1)

Copied to clipboard

Challenge: a new method to extract user attributes from dialogues is needed to improve user understanding.
Approach: They propose to leverage dialogues with conversational agents to automatically extract user attributes from dialogues.
Outcome: The proposed model surpasses retrieval and generation baselines on human evaluation.
ChatGPT Role-play Dataset: Analysis of User Motives and Model Naturalness (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in interactive large language models like ChatGPT have revolutionized various domains, but their behavior in natural and role-play settings remains underexplored.
Approach: They analyze ChatGPT interactions in a normal way and a role-play setting to examine its behavior in conversational settings.
Outcome: The proposed dataset shows that chatGPT behaves in natural and role-play settings with different user motives and model naturalness.
Recipes for Building an Open-Domain Chatbot (2021.eacl-main)

Copied to clipboard

Challenge: Existing work shows that scaling models in the number of parameters and the size of the data they are trained on gives improved results, but other factors are important.
Approach: They propose to build open-domain chatbots that can be scaled to improve their performance . they use a blend of cognitive and cognitive skills to build a model that combines these skills .
Outcome: The proposed models outperform existing approaches in multi-turn dialogue on engagingness and humanness measurements.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations