Papers by Debjit Paul
Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization (2026.acl-long)
Copied to clipboard
Negar Foroutan, Clara Meister, Debjit Paul, Joel Niklaus, Sina Ahmadi, Antoine Bosselut, Rico Sennrich
| Challenge: | Tokenization is the first step of most NLP pipelines. |
| Approach: | They propose a parity-aware byte pair encoder that maximizes the compression gain of the currently worst-compressed language for cross-lingual parity. |
| Outcome: | a new algorithm reduces tokenization inequality by 89% compared to classical BPE . the proposed algorithm is based on a fair-max rule that maximizes the compression gain of the currently worst-compressed language . |
Exploring Defeasibility in Causal Reasoning (2024.findings-acl)
Copied to clipboard
Shaobo Cui, Lazar Milikic, Yiyang Feng, Mete Ismayilzada, Debjit Paul, Antoine Bosselut, Boi Faltings
| Challenge: | Existing studies ignore defeasibility in causal reasoning and fail to evaluate existing causal strength metrics in defensible settings. |
| Approach: | They propose a metric that measures causal strength based on token-level causal relationships. |
| Outcome: | The proposed metric improves on existing metrics by 69.7% . supporters and defeaters are more effective than opponents, the authors show . |
Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs (N19-1)
Copied to clipboard
| Challenge: | Existing methods to categorize sentiments and emotions in text are limited. |
| Approach: | They propose to extract, rank, filter and select multi-hop relation paths from a commonsense knowledge resource to interpret the expression of sentiment in terms of their underlying human needs. |
| Outcome: | The proposed method improves on a recently published dataset for categorizing human needs. |
CRAB: Assessing the Strength of Causal Relationships Between Real-world Events (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for reasoning about events in narratives do not understand the complexity of the causal relationships of events in the narrative. |
| Approach: | They propose a Causal Reasoning Assessment Benchmark to evaluate causal understanding of events in narratives. |
| Outcome: | The proposed model performs worse when models are derived from complex causal structures than simple linear causal chains. |
Process Evaluation for Agentic Systems (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent adoption of LLM-based assistants has led to premature assumptions about their reliability and general capability. |
| Approach: | They propose to assess the feasibility of automatic process evaluation for critical applications such as medicine, finance, law and infrastructure. |
| Outcome: | The proposed evaluations are based on a small-scale study to assess the feasibility of automated process evaluation, present a compliance score, analyse use cases of bad and good behaviours, and offer recommendations for more holistic evaluation. |
Entity Insertion in Multilingual Linked Corpora: The Case of Wikipedia (2024.emnlp-main)
Copied to clipboard
| Challenge: | a new task for entity insertion in information networks is needed to integrate entities into multilingual linked corpora . text spans in the source and target entities are not available to insert a link to the target entity . a benchmark dataset in 105 languages is used to study the problem of entity inserted in information systems . |
| Approach: | They propose a framework for entity insertion that integrates entities into linked corpora . they compile a benchmark dataset in 105 languages and test it in a zero-shot manner . |
| Outcome: | The proposed framework outperforms baseline models on languages not seen during training with minimal performance drop. |
Language Model Decoding as Likelihood–Utility Alignment (2023.findings-eacl)
Copied to clipboard
Martin Josifoski, Maxime Peyrard, Frano Rajič, Jiheng Wei, Debjit Paul, Valentin Hartmann, Barun Patra, Vishrav Chaudhary, Emre Kiciman, Boi Faltings
| Challenge: | Existing studies only compare decoding algorithms in narrow scenarios, and their findings do not generalize across tasks. |
| Approach: | They propose a taxonomy of misalignment mitigation strategies to provide a unifying view of decoding as a tool for alignment. |
| Outcome: | The proposed taxonomy combines likelihood and utility assumptions to provide general statements about decoding as a tool for alignment across tasks. |
A Logical Fallacy-Informed Framework for Argument Generation (2025.naacl-long)
Copied to clipboard
| Challenge: | Argument generation is crucial in daily life and has numerous online and offline applications. |
| Approach: | They propose a fallacy-informed preference optimization that includes a classification loss to capture the fine-grained information on fallacy types to help LLMs generate logically sound arguments. |
| Outcome: | The proposed method reduces fallacy errors by 17.5% on argument generation tasks and outperforms fine-tuned baselines and other preference optimization methods, such as DPO. |
COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion (2021.acl-long)
Copied to clipboard
| Challenge: | Existing inference models are opaque, but they can be made more interpretable by explicitly generating interim inference rules and using them to guide the generation of task-specific textual outputs. |
| Approach: | They propose a recursive inference framework that iteratively reads context sentences and dynamically generates contextualized inference rules, encodes them, and uses them to guide output generation. |
| Outcome: | The proposed framework generates better story sentences than baseline models, and is more interpretable than existing models. |
Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling (N19-3)
Copied to clipboard
| Challenge: | In low-resource environments, self-training is less effective due to unreliable annotations . we combine self-teaching with noise handling to clean the self-labeled data . |
| Approach: | They propose to combine self-training with noise handling to clean unlabeled data . they propose to model clean and noisy labels separately to improve performance . |
| Outcome: | The proposed method performs better than baseline methods on Chunking and NER. |
CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent efforts in natural language processing (NLP) commonsense reasoning research have produced a number of new datasets and benchmarks. |
| Approach: | They propose a manually-curated, multi-task benchmark that evaluates models' ability to apply commonsense reasoning in the context of six real-world NLP tasks. |
| Outcome: | The proposed benchmark evaluates the ability of models to apply commonsense reasoning in the context of six real-world NLP tasks. |
Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are shown to perform better when asked to reason step-by-step before generating a final answer. |
| Approach: | They propose a framework to tailor small-sized LMs to generate correct reasoning steps and robustly reason over these steps. |
| Outcome: | The proposed framework outperforms four competitive baselines and improves the robustness and generalization ability of the reasoning LM, yielding higher performance on out-of-distribution test sets. |
Generating Hypothetical Events for Abductive Inference (2021.starsem-1)
Copied to clipboard
| Challenge: | Abductive reasoning is inference to the best explanation given an incomplete set of observations about everyday situations. |
| Approach: | They propose a model that generates what could happen next from a hypothetical scenario and then proposes the most plausible explanation from varying hypothetical scenarios. |
| Outcome: | The proposed model improves over previous vanilla pre-trained models fine-tuned on Abductive NLI. |
Social Commonsense Reasoning with Multi-Head Knowledge Attention (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills. |
| Approach: | They propose a multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell. |
| Outcome: | The proposed model improves performance on two reasoning tasks that require different reasoning skills. |
REFINER: Reasoning Feedback on Intermediate Representations (2024.eacl-long)
Copied to clipboard
Debjit Paul, Mete Ismayilzada, Maxime Peyrard, Beatriz Borges, Antoine Bosselut, Robert West, Boi Faltings
| Challenge: | Language models (LLMs) have shown remarkable performance by explicitly generating intermediate inferences,e.g., chain-of-thought prompting. |
| Approach: | They propose a framework for finetuning LMs to generate intermediate reasoning steps while interacting with a critic model that provides automated feedback on the reasoning. |
| Outcome: | Empirical evaluations of REFINER on three diverse reasoning tasks show that it significantly improves over baseline models. |