Eric Michael Smith
8 papers · 2019–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird
📈
Trend Setter
Top co-authors
Research topics
Keywords
demographic bia
(2)
conversational agent
(2)
adversarial attack
(2)
language model
(2)
conversational ai
(1)
dialogue generation
(1)
text generation
(1)
bias detection
(1)
model aggregation
(1)
affective computing
(1)
model alignment
(1)
vision-language model
(1)
multi-turn dialogue
(1)
fairness evaluation
(1)
dialogue system
(1)
open-domain dialogue
(1)
text perturbation
(1)
open-domain conversation
(1)
domain-adaptive pre-training
(1)
multi-task training
(1)
Papers
Backtracking Improves Generation Safety
ICLR 2025
Persistent Pre-training Poisoning of LLMs
ICLR 2025
“I’m sorry to hear that”: Finding New Biases in Language Models with a Holistic Descriptor Dataset
EMNLP 2022
Perturbation Augmentation for Fairer NLP
EMNLP 2022
Multi-Modal Open-Domain Dialogue
EMNLP 2021
Recipes for Building an Open-Domain Chatbot
EACL 2021
Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills
ACL 2020
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset
ACL 2019