publications
publications by categories in reversed chronological order.
Visit Google Scholar for a full list.
2024
- ArXiv, 2024
💡 LLM probabilities are predictive of the correctness of their answers on Q&A tasks
- ArXiv, 2024
💡 Models that can read texts to simulate environments
2023
- Workshop on Intrinsically Motivated Open-ended Learning (NeurIPS), 2023
💡 Learn increasingly abstract language to reduce communication effort
- EMNLP Findings, 2023
💡 Detect hallucinations in model-generated navigation instructions
- Workshop on Theory of Mind (ICML), 2023
💡 LLMs as limited communicative agents and how to augment them
- Define, evaluate, and improve task-oriented cognitive capabilities for instruction generation modelsACL Findings, 2023
💡 Improve instruction generation by predicting human interpretation
2022
- ICML, Jul 2022
💡 Agents that can decide when and what question to ask, and incoporate answer to make progress
2021
- ICML, Jul 2021
💡 Framework for learning from language feedback with theoretical guarantees
2019
- EMNLP, 2019
💡 Agents that can ask for help and interpret language instructions
- CVPR, 2019
💡 Agent that can ask for help
- New Frontiers in Summarization Workshop at EMNLP, Nov 2019
💡 Evaluation dataset for cross-lingual summarization
2017
- EMNLP, Sep 2017
💡 Improve machine translation with reinforcement learning from noisy ratings
-
2015
- EMNLP, Sep 2015
💡 Calibrated probabilities for detecting errors of NLP models