Safety for E2E Conversational AI
SIGDial 2021 Special Session
Recent progress in end-to-end (E2E) open-domain dialogue agents has shown a dramatic improvement in the ability of these models to learn patterns and mimic conversational behaviors from the training data. Unfortunately these models still exhibit many concerning problems. First, they may learn undesirable features present in the training data such as biased, toxic, or otherwise harmful language. Second, they do not respond reliably in safety critical situations, such as the user asking for medical advice, indicating intention of self-harm, or during public health crises such as COVID-19.
These problems are difficult, as what is deemed as “offensive” or even “sensitive” is both contextually and culturally dependent, and picking up on more subtle examples of unsafe language often requires a level of language understanding that is well beyond current capabilities.
A first workshop was held to discuss these topics on October 2020. Following on from that, this special session will take place at SIGDial 2021.
Location, format, and schedule
SafeConvAI Special Session @ SIGDial 2021 will be an all-virtual event.
The special session will consist of a keynote, a panel, lightning talks, oral and poster paper presentations.
Laurence Devillers, Paris-Sorbonne
Laurence Devillers is a full Professor of Artificial Intelligence at Sorbonne University and heads the team of research "Affective and social dimensions in Spoken interaction with (ro)bots: ethical issues" at CNRS-LISN (Saclay). Since 2020, she heads the interdisciplinary Chair on Artificial Intelligence HUMAAINE: HUman-MAchine Affective INteraction & Ethics (2020-24) at CNRS. Her topics of research are Human-Machine Co-adaptation: from the modeling of emotions and human-robot dialogue to the ethical impacts for society and the risks and benefits of AI notably for vulnerable people. She is a member of National Comity Pilot on Ethics of Numeric (CNPEN) working on conversational Agents, social robots, AI and Ethics. She is now an expert member of the GPAI on "the future of work" since June 2020 (international group). In March 2020, she wrote the book “Les robots émotionnels” (Ed. L’Observatoire) and in March 2017 “Des Robots et des Hommes: mythes, fantasmes et réalité” (Ed. Plon) for explaining the urgency of building Social and Affective Robotic/AI Systems with Ethics by design.
Our objectives for this special session are:
To showcase recent and ongoing work related to building safer conversational AI systems
To bridge the gap between dialogue and neighboring disciplines, such as safety security, computational social science, policy, ethics, applications such as health, etc.
To identify paths forward for more responsible conversational AI research
Call for papers
Long papers must describe substantial, original, completed, and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included. These papers will undergo the same peer-review process by the SIGDial program committee as papers submitted to the main SIGdial track. These papers will appear in the main SIGdial proceedings and are presented with the main track. Long papers must be no longer than 8 pages, including title, text, figures, and tables. An unlimited number of pages is allowed for references. Two additional pages are allowed for appendices containing sample discourses/dialogues and algorithms, and an extra page is allowed in the final version to address reviewers’ comments.
Short papers must describe original and unpublished work. These papers would go through the same peer-review process by the SIGDial program committee as papers submitted to the main SIGdial track. These papers will appear in the main SIGdial proceedings and are presented with the main track. Please note that a short paper is not a shortened long paper. Instead, short papers should have a point that can be made in a few pages, such as a small, focused contribution; a negative result; or an interesting application nugget. It should be no longer than 4 pages, including title, text, figures, and tables. An unlimited number of pages is allowed for references. One additional page is allowed for sample discourses/dialogues and algorithms, and an extra page is allowed in the final version to address reviewers’ comments. An unlimited number of pages are allowed for references.
Late-breaking and Work-in-progress abstracts will showcase ongoing work and focused relevant contributions. Submissions need not present original work. Late-breaking and work-in-progress abstracts should be no longer than 1 page. The submissions will be reviewed by the SafeConvAI program committee and posted on the special session website. Abstracts will be presented as lightning talks and/or posters during the session. Authors will retain the copyright to their work so that they may submit to other venues as their work matures.
Gavin Abercrombie, Heriot-Watt University
Y-Lan Boureau, Facebook AI
Emily Dinan, Facebook AI
Saadia Gabriel, University of Washington
Alborz Geramifard, Facebook AI
Verena Rieser, Heriot-Watt University
Yulia Tsvetkov, Carnegie Mellon University
Zeerak Waseem, University of Sheffield
Senior advisory board
Barbara Grosz, Harvard University
Pilar Manchón, Google
Ehud Reiter, University of Aberdeen
Jason Williams, Apple
Contact the organisers at firstname.lastname@example.org