Jason Weston

Chain-of-Verification Reduces Hallucination in Large Language Models ACL 2024 Leveraging Implicit Feedback from Deployment Data in Dialogue EACL 2024 System-Level Natural Language Feedback EACL 2024 When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels NAACL 2024 The ART of LLM Refinement: Ask, Refine, and Trust NAACL 2024 Branch-Solve-Merge Improves Large Language Model Evaluation and Generation NAACL 2024 Iterative Reasoning Preference Optimization NIPS 2024 Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback ACL 2023 Learning to Reason and Memorize with Self-Notes NIPS 2023 The CRINGE Loss: Learning what language not to model ACL 2023 Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity NAACL 2022 Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents ACL 2022 Beyond Goldfish Memory: Long-Term Open-Domain Conversation ACL 2022 Director: Generator-Classifiers For Supervised Language Modeling AACL 2022 Internet-Augmented Dialogue Generation ACL 2022 Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion EMNLP 2022 Director: Generator-Classifiers For Supervised Language Modeling IJCNLP 2022 Reason first, then respond: Modular Generation for Knowledge-infused Dialogue EMNLP 2022 Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots ACL 2021 Hash Layers For Large Sparse Models NIPS 2021 Multi-Modal Open-Domain Dialogue EMNLP 2021 Retrieval Augmentation Reduces Hallucination in Conversation EMNLP 2021 I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling ACL 2021 Bot-Adversarial Dialogue for Safe Conversational Agents NAACL 2021 How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds NAACL 2021 Recipes for Building an Open-Domain Chatbot EACL 2021 I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling IJCNLP 2021 Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots IJCNLP 2021 Not All Memories are Created Equal: Learning to Forget by Expiring ICML 2021 Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring ICLR 2020 Generating Interactive Worlds with Text AAAI 2020 Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills ACL 2020 Image-Chat: Engaging Grounded Conversations ACL 2020 The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents ACL 2020 Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training ACL 2020 Adversarial NLI: A New Benchmark for Natural Language Understanding ACL 2020 Multi-Dimensional Gender Bias Classification EMNLP 2020 Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation EMNLP 2020 Neural Text Generation With Unlikelihood Training ICLR 2020 Dialogue Natural Language Inference ACL 2019 Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack IJCNLP 2019 ELI5: Long Form Question Answering ACL 2019 Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack EMNLP 2019 Wizard of Wikipedia: Knowledge-Powered Conversational Agents ICLR 2019 Finding Generalizable Evidence by Learning to Convince Q&A Models IJCNLP 2019 Learning to Speak and Act in a Fantasy Text Adventure Game IJCNLP 2019 Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue IJCNLP 2019 Engaging Image Captioning via Personality CVPR 2019 What makes a good conversation? How controllable attributes affect human judgments NAACL 2019 Learning from Dialogue after Deployment: Feed Yourself, Chatbot! ACL 2019 Learning to Speak and Act in a Fantasy Text Adventure Game EMNLP 2019 Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue EMNLP 2019 Finding Generalizable Evidence by Learning to Convince Q&A Models EMNLP 2019 Emergent Translation in Multi-Agent Communication ICLR 2018 Personalizing Dialogue Agents: I have a dog, do you have pets too? ACL 2018 Jump to better conclusions: SCAN both left and right EMNLP 2018 Retrieve and Refine: Improved Sequence Generation Models For Dialogue EMNLP 2018 Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent ICLR 2018 Reading Wikipedia to Answer Open-Domain Questions ACL 2017 ParlAI: A Dialog Research Software Platform EMNLP 2017 Key-Value Memory Networks for Directly Reading Documents EMNLP 2016 Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution IJCNLP 2015 End-To-End Memory Networks NIPS 2015 Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution ACL 2015 A Neural Attention Model for Abstractive Sentence Summarization EMNLP 2015 Training Highly Multiclass Classifiers JMLR 2014 Affinity Weighted Embedding ICML 2014 Semantic Frame Identification with Distributed Word Representations ACL 2014 Embedding Methods for Natural Language Processing EMNLP 2014 #TagSpace: Semantic Embeddings from Hashtags EMNLP 2014 Question Answering with Subgraph Embeddings EMNLP 2014 Label Partitioning For Sublinear Ranking ICML 2013 Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction EMNLP 2013 Translating Embeddings for Modeling Multi-relational Data NIPS 2013 Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing AISTATS 2012 Natural Language Processing (Almost) from Scratch JMLR 2011 Label Embedding Trees for Large Multi-Class Tasks NIPS 2010 Towards Understanding Situated Natural Language AISTATS 2010 Half Transductive Ranking AISTATS 2010 Polynomial Semantic Indexing NIPS 2009 Multi-class Protein Classification Using Adaptive Codes JMLR 2007 Fast Semantic Extraction Using a Novel Neural Network Architecture ACL 2007 Large Scale Transductive SVMs JMLR 2006 Fast Kernel Classifiers with Online and Active Learning JMLR 2005 Use of the Zero-Norm with Linear Models and Kernel Methods JMLR 2003