Publications

Selected Publications and Preprints

2024

  1. Frodo.png
    Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
    Debjit PaulRobert WestAntoine Bosselut, and Boi Faltings
    In , Feb 2024
  2. defeasible.png
    δ-CAUSAL: Exploring Defeasibility in Causal Reasoning
    Shaobo Cui, Lazar Milikic, Yiyang Feng, Mete Ismayilzada, Debjit PaulAntoine Bosselut, and Boi Faltings
    In , Jan 2024
  3. Refiner.png
    REFINER: Reasoning Feedback on Intermediate Representations
    Debjit Paul, Mete Ismayilzada, Maxime Peyrard, Beatriz Borges, Antoine BosselutRobert West, and Boi Faltings
    In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), Mar 2024

2023

  1. CRAB.png
    CRAB: Assessing the Strength of Causal Relationships Between Real-world Events
    Angelika Romanou, Syrielle Montariol*, Debjit Paul*, Léo Laugier, Karl Aberer, and Antoine Bosselut
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), Dec 2023
  2. CROW.png
    CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks
    Mete Ismayilzada, Debjit Paul, Syrielle Montariol, Mor Geva, and Antoine Bosselut
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), Dec 2023
  3. Flows.png
    Flows: Building Blocks of Reasoning and Collaborating AI
    Martin Josifoski, Lars Klein, Maxime Peyrard, Yifei Li, Saibo Geng, Julian Paul Schnitzler, Yuxing Yao, Jiheng Wei, Debjit Paul, and Robert West
    Aug 2023
  4. Alignment.png
    Language Model Decoding as Likelihood–Utility Alignment
    Martin Josifoski, Maxime Peyrard, Frano Rajič, Jiheng Wei, Debjit Paul, Valentin Hartmann, Barun Patra, Vishrav Chaudhary, Emre Kiciman, Robert West, and Boi Faltings
    In Findings of the Association for Computational Linguistics: EACL 2023, May 2023

2022

  1. class_incremental.png
    Class Incremental Learning for Intent Classification with Limited or No Old Data
    Debjit Paul, Daniil Sorokin, and Judith Gaspers
    In Proceedings of the The First Workshop on Ever Evolving NLP (EvoNLP), Dec 2022

2021

  1. COINS.png
    COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion
    Debjit Paul, and Anette Frank
    In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Aug 2021
  2. knowledge_graph.png
    CO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts
    Maria Becker, Katharina Korfhage, Debjit Paul, and Anette Frank
    In Proceedings of the 14th International Conference on Computational Semantics (IWCS), Jun 2021
  3. starsem.png
    Generating Hypothetical Events for Abductive Inference
    Debjit Paul, and Anette Frank
    In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, Aug 2021

2020

  1. model_emlp_2020.png
    Social Commonsense Reasoning with Multi-Head Knowledge Attention
    Debjit Paul, and Anette Frank
    In Findings of the Association for Computational Linguistics: EMNLP 2020, Nov 2020

2019

  1. MTL_naacl_srw.png
    Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling
    Debjit Paul, Mittul Singh, Michael A. Hedderich, and Dietrich Klakow
    In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, Jun 2019
  2. naacl2019.png
    Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs
    Debjit Paul, and Anette Frank
    In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Jun 2019