36 citations · 92 across the 17 of their papers we have counts for
20 papers
A Benchmark for Deep Information Synthesis
Debjit Paul, Daniel Murphy, Milan Gritta +14
Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current e…
Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization
Negar Foroutan, Clara Meister, Debjit Paul +4
Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines. Standard algorithms for learning tokenizers rely on frequency-based objectives, which favor…
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
Angelika Romanou, Negar Foroutan, Anna Sotnikova +56
The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal val…
Entity Insertion in Multilingual Linked Corpora: The Case of Wikipedia
Tomás Feith, Akhil Arora, Martin Gerlach +2
Links are a fundamental part of information networks, turning isolated pieces of knowledge into a network of information that is much richer than the sum of its parts. However, add…
Creativity in AI: Progresses and Challenges
Mete Ismayilzada, Debjit Paul, Antoine Bosselut +1
Creativity is the ability to produce novel, useful, and surprising ideas, and has been widely studied as a crucial aspect of human cognition. Machine creativity on the other hand h…
Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants
Beatriz Borges, Negar Foroutan, Deniz Bayazit +87
AI assistants are being increasingly used by students enrolled in higher education institutions. While these tools provide opportunities for improved teaching and education, they a…
A Logical Fallacy-Informed Framework for Argument Generation
Luca Mouchel, Debjit Paul, Shaobo Cui +3
Despite the remarkable performance of Large Language Models (LLMs) in natural language processing tasks, they still struggle with generating logically sound arguments, resulting in…
Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
Debjit Paul, Robert West, Antoine Bosselut +1
Large language models (LLMs) have been shown to perform better when asked to reason step-by-step before answering a question. However, it is unclear to what degree the model's fina…
Exploring Defeasibility in Causal Reasoning
Shaobo Cui, Lazar Milikic, Yiyang Feng +4
Defeasibility in causal reasoning implies that the causal relationship between cause and effect can be strengthened or weakened. Namely, the causal strength between cause and effec…
CRAB: Assessing the Strength of Causal Relationships Between Real-world Events
Angelika Romanou, Syrielle Montariol, Debjit Paul +3
Understanding narratives requires reasoning about the cause-and-effect relationships between events mentioned in the text. While existing foundation models yield impressive results…
CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks
Mete Ismayilzada, Debjit Paul, Syrielle Montariol +2
Recent efforts in natural language processing (NLP) commonsense reasoning research have yielded a considerable number of new datasets and benchmarks. However, most of these dataset…
Flows: Building Blocks of Reasoning and Collaborating AI
Martin Josifoski, Lars Klein, Maxime Peyrard +8
Recent advances in artificial intelligence (AI) have produced highly capable and controllable systems. This creates unprecedented opportunities for structured reasoning as well as…
REFINER: Reasoning Feedback on Intermediate Representations
Debjit Paul, Mete Ismayilzada, Maxime Peyrard +4
Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, the…
Language Model Decoding as Likelihood-Utility Alignment
Martin Josifoski, Maxime Peyrard, Frano Rajic +8
A critical component of a successful language generation pipeline is the decoding algorithm. However, the general principles that should guide the choice of a decoding algorithm re…
Generating Hypothetical Events for Abductive Inference
Debjit Paul, Anette Frank
Abductive reasoning starts from some observations and aims at finding the most plausible explanation for these observations. To perform abduction, humans often make use of temporal…
COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion
Debjit Paul, Anette Frank
Despite recent successes of large pre-trained language models in solving reasoning tasks, their inference capabilities remain opaque. We posit that such models can be made more int…
CO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts
Maria Becker, Katharina Korfhage, Debjit Paul +1
In this work we leverage commonsense knowledge in form of knowledge paths to establish connections between sentences, as a form of explicitation of implicit knowledge. Such connect…
Social Commonsense Reasoning with Multi-Head Knowledge Attention
Debjit Paul, Anette Frank
Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills. In this work w…
Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs
Debjit Paul, Anette Frank
To make machines better understand sentiments, research needs to move from polarity identification to understanding the reasons that underlie the expression of sentiment. Categoriz…
Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling
Debjit Paul, Mittul Singh, Michael A. Hedderich +1
In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount…