Papers by Antoine Bosselut

Modeling Naive Psychology of Characters in Simple Commonsense Stories (P18-1)

Challenge:	Pretrained language models encode implicit representations of knowledge in their parameters, but localizing these representations and disentangling them from each other remains an open problem.
Approach:	They propose a masking scheme that can be applied to weights and neurons to discover such subnetworks.
Outcome:	The proposed method can remove specific knowledge from models while minimizing adverse effects on the original model.

Copied to clipboard

Hannah Rashkin, Antoine Bosselut, Maarten Sap, Kevin Knight, Yejin Choi

Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs (2024.acl-long)

Challenge:	Understanding a narrative requires reasoning about the causal links between the events in the story and the mental states of the characters, even when those relationships are not explicitly stated.
Approach:	They propose a new annotation framework to explain naive psychology of story characters as fully-specified chains of mental states with respect to motivations and emotional reactions.
Outcome:	The proposed framework provides a baseline performance on several new tasks suggesting avenues for future research.

Copied to clipboard

Tianqing Fang, Zeming Chen, Yangqiu Song, Antoine Bosselut

Discourse Understanding and Factual Consistency in Abstractive Summarization (2021.eacl-main)

Challenge:	Currently, language models struggle to generate commonsense inferences for complex tasks due to data scarcity and the difficulty of reasoning over multiple pieces of information.
Approach:	They propose a dataset to generate commonsense inferences from commonsensible data . they use a commonsence knowledge graph to extract and form questions from existing commonseense knowledge graphs.
Outcome:	The proposed dataset improves the ability of language models to reason about complex events without expensive human annotations.

Copied to clipboard

Saadia Gabriel, Antoine Bosselut, Jeff Da, Ari Holtzman, Jan Buys, Kyle Lo, Asli Celikyilmaz, Yejin Choi

Summarization

Challenge:	Existing abstractive summarization models often hallucinate information or generate factually incorrect summaries.
Approach:	They propose a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary.
Outcome:	The proposed framework generates abstracts with factual consistency and coherence significantly better than baselines.

Efficient Tool Use with Chain-of-Abstraction Reasoning (2025.coling-main)

Copied to clipboard

Silin Gao, Jane Dwivedi-Yu, Ping Yu, Xiaoqing Ellen Tan, Ramakanth Pasunuru, Olga Golovneva, Koustuv Sinha, Asli Celikyilmaz, Antoine Bosselut, Tianlu Wang

Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization (2026.acl-long)

Challenge:	Recent large language models have made progress at interpreting and executing instructions.
Approach:	They propose a method to decouple general reasoning from specialized knowledge . they propose to use abstract reasoning chains and domain tools to reify each chain .
Outcome:	The proposed method outperforms baseline methods on QA and mathematical reasoning domains.

Copied to clipboard

Negar Foroutan, Clara Meister, Debjit Paul, Joel Niklaus, Sina Ahmadi, Antoine Bosselut, Rico Sennrich

DiffuCOMET: Contextual Commonsense Knowledge Diffusion (2024.acl-long)

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 .

Copied to clipboard

Silin Gao, Mete Ismayilzada, Mengjie Zhao, Hiromi Wakaki, Yuki Mitsufuji, Antoine Bosselut

RLMEval: Evaluating Research-Level Neural Theorem Proving (2025.findings-emnlp)

Challenge:	Recent methods for identifying contextually relevant commonsense inferences are weak . knowledge models are trained to verbalize tuples from general commonsens knowledge graphs .
Approach:	They develop a series of knowledge models that leverage diffusion to reconstruct semantic connections between narrative contexts and relevant commonsense knowledge.
Outcome:	The proposed model improves on two benchmarks, ComFact and WebNLG+, to measure commonsense diversity and contextual relevance.

Copied to clipboard

Auguste Poiroux, Antoine Bosselut, Viktor Kunčak

DISCO: Distilling Counterfactuals with Large Language Models (2023.acl-long)

Challenge:	RLMEval evaluates large language models for research-level neural theorem proving and proof autoformalization . the best model achieves only a 10.3% pass rate on existing benchmarks .
Approach:	They propose a new evaluation suite for large language models . it evaluates research-level theorems from real-world Lean formalization projects .
Outcome:	RLMEval evaluates research-level theorems from real-world Lean formalization projects.

Copied to clipboard

Zeming Chen, Qiyue Gao, Antoine Bosselut, Ashish Sabharwal, Kyle Richardson

Tracking the Limits of Knowledge Propagation: How LLMs Fail at Multi-Step Reasoning with Conflicting Knowledge (2026.eacl-long)

Challenge:	high-quality counterfactual data is scarce for most tasks and not easily generated at scale.
Approach:	They propose a method for automatically generating high-quality counterfactual data at scale . they use a large general language model to generate phrasal perturbations and filter them .
Outcome:	The proposed method is task-agnostic and can be applied to the task of natural language inference.

Copied to clipboard

Yiyang Feng, Zeming Chen, Haotian Wu, Jiawei Zhou, Antoine Bosselut

“I’m Not Mad”: Commonsense Implications of Negation and Contradiction (2021.naacl-main)

Challenge:	Existing benchmarks for analyzing the performance of Large Language Models (LLMs) focus on single knowledge updates and fact recall, but do not consider how these updates affect downstream reasoning.
Approach:	They propose a benchmark to study how LLMs propagate new knowledge when it conflicts with the model's parametric knowledge.
Outcome:	The proposed benchmark compared models with no updated facts to show that the new methods worsen performance and improve reasoning performance.

Copied to clipboard

Liwei Jiang, Antoine Bosselut, Chandra Bhagavatula, Yejin Choi

Counterfactual Story Reasoning and Generation (D19-1)

Challenge:	a new commonsense knowledge graph for negated and contradicted events is developed to help humans reason about their underlying causes and effects.
Approach:	They propose a new commonsense knowledge graph with 624K if-then rules focusing on negated and contradictory events.
Outcome:	The proposed model can be used to analyze negated and contradicted statements in natural language.

Copied to clipboard

Lianhui Qin, Antoine Bosselut, Ari Holtzman, Chandra Bhagavatula, Elizabeth Clark, Yejin Choi

Text Generation

Challenge:	a desired property of AI systems is counterfactual reasoning: ability to predict causal changes in future events.
Approach:	They propose to rewrite a short story and a counterfactual event to make it compatible with the given counterfact.
Outcome:	The proposed task requires deep understanding of causal narrative chains and counterfactual invariance . the proposed dataset includes 81,407 counterfact "branches" without a rewritten storyline .

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

The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units (2025.naacl-long)

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 .

Copied to clipboard

Badr AlKhamissi, Greta Tuckute, Antoine Bosselut, Martin Schrimpf

Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings (2025.emnlp-main)

Challenge:	Recent advances in large language models (LLMs) have revealed their potential to perform far more than language processing tasks, showcasing abilities in reasoning and problem-solving.
Approach:	They identify language-selective units within 18 popular LLMs using the same localization approach that is used in neuroscience.
Outcome:	The proposed method shows that language-selective units are more aligned to brain recordings from the human language system than random units.

Copied to clipboard

Max Conti, Manuel Faysse, Gautier Viaud, Antoine Bosselut, Celine Hudelot, Pierre Colombo

Information Retrieval

Challenge:	Modern document retrieval embedding methods typically encode passages (chunks) from documents independently, often overlooking contextual information from the rest of the document.
Approach:	They propose a benchmark to evaluate retrieval models' ability to leverage document-wide context.
Outcome:	The proposed method significantly improves retrieval quality on ConTEB without sacrificing base model performance.

ConLID: Supervised Contrastive Learning for Low-Resource Language Identification (2026.eacl-long)

Copied to clipboard

Negar Foroutan, Jakhongir Saydaliev, Grace Kim, Antoine Bosselut

CRAB: Assessing the Strength of Causal Relationships Between Real-world Events (2023.emnlp-main)

Challenge:	Low-resource languages and dialects remain difficult to identify and categorize accurately due to data in these languages and are limited to single-domain data.
Approach:	They propose a supervised contrastive learning approach to learn domain-invariant representations for low-resource languages by 3.2 percentage points while maintaining its performance for the high-resourced languages.
Outcome:	The proposed approach improves LID performance on out-of-domain data for low-resource languages by 3.2 percentage points while maintaining its performance for the high-resourced languages.

Copied to clipboard

Angelika Romanou, Syrielle Montariol, Debjit Paul, Leo Laugier, Karl Aberer, Antoine Bosselut

From Language to Cognition: How LLMs Outgrow the Human Language Network (2025.emnlp-main)

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.

Copied to clipboard

Badr AlKhamissi, Greta Tuckute, Yingtian Tang, Taha Osama A Binhuraib, Antoine Bosselut, Martin Schrimpf

Challenge:	Large language models exhibit remarkable similarity to neural activity in the human language network, but their properties remain unclear.
Approach:	They benchmark 34 training checkpoints spanning 300B tokens across 8 different model sizes . they find that brain alignment tracks the development of formal linguistic competence more closely than functional linguistic competency.
Outcome:	The results show that large language models exhibit similarity to human language networks . they show that the correlation between next-word prediction and brain alignment fades once models surpass human language proficiency.

PICLe: Pseudo-annotations for In-Context Learning in Low-Resource Named Entity Detection (2025.naacl-long)

Copied to clipboard

Sepideh Mamooler, Syrielle Montariol, Alexander Mathis, Antoine Bosselut

Low-Resource NLP

Challenge:	In-context learning is sensitive to the choice of demonstrations and can be used for tasks with few examples.
Approach:	They propose a framework for in-context learning with noisy, pseudo-annotated demonstrations . they annotate large quantities of demonstrations in a zero-shot first pass .
Outcome:	The proposed framework outperforms ICL on biomedical NED datasets with zero human-annotation.

COMET: Commonsense Transformers for Automatic Knowledge Graph Construction (P19-1)

Copied to clipboard

Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, Yejin Choi

ComFact: A Benchmark for Linking Contextual Commonsense Knowledge (2022.findings-emnlp)

Challenge:	Existing studies on commonsense knowledge base construction only store loosely structured open-text descriptions of knowledge.
Approach:	They propose a commonsense knowledge base construction model that generates rich commonsensense descriptions in natural language.
Outcome:	The proposed models can generate rich and diverse commonsense descriptions in natural language.

Copied to clipboard

Silin Gao, Jena D. Hwang, Saya Kanno, Hiromi Wakaki, Yuki Mitsufuji, Antoine Bosselut

Natural Language Interfaces

Challenge:	Existing methods to retrieve facts from commonsense knowledge graphs are imprecise, requiring heuristics that ignore contexts and ambiguity . a novel benchmark, ComFact, contains 293k in-context relevance annotations for commonsensense triplets .
Approach:	They propose a task of commonsense fact linking where models are given contexts and trained to identify situationally-relevant commonsensical knowledge from KGs.
Outcome:	The proposed benchmark shows that heuristic fact linking approaches are imprecise . however, the models still significantly underperform humans in the commonsense augmentation task .

Reliable Evaluation and Benchmarks for Statement Autoformalization (2025.emnlp-main)

Copied to clipboard

Auguste Poiroux, Gail Weiss, Viktor Kunčak, Antoine Bosselut

Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules (2021.emnlp-main)

Challenge:	Existing methods for evaluating statement autoformalization are limited . current methods can achieve up to 45.1% accuracy on undergraduate mathematics .
Approach:	They propose a new autoformalization metric that correlates strongly with human judgment . they propose two new auto-formalisation benchmarks: ProofNet# and RLM25 .
Outcome:	The proposed methods can achieve up to 45.1% accuracy on undergraduate mathematics but struggle with research-level content without proper context.

Copied to clipboard

Forough Arabshahi, Jennifer Lee, Antoine Bosselut, Yejin Choi, Tom Mitchell

Natural Language Interfaces

Challenge:	Currently, conversational agents lack commonsense reasoning, preventing them from engaging in rich conversations with humans.
Approach:	They propose a commonsense reasoning system that uncovers unstated presumptions from user commands satisfying a general template of if-(state), then-(action), because-(goal) They propose to use a transformer-based generative commons sense knowledge base as its source of background knowledge to extract multi-hop reasoning chains from the neural KB.
Outcome:	The proposed model achieves a 35% higher success rate than existing methods with human users.

Conditional set generation using Seq2seq models (2022.emnlp-main)

Copied to clipboard

Aman Madaan, Dheeraj Rajagopal, Niket Tandon, Yiming Yang, Antoine Bosselut

Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining (2026.acl-long)

Challenge:	Several NLP tasks are instances of set generation.
Approach:	They propose a model-independent data augmentation approach that enlarges the model with the signals of order-invariance and cardinality.
Outcome:	The proposed method improves performance on four benchmark datasets with no additional annotations.

Copied to clipboard

Deniz Bayazit, Aaron Mueller, Antoine Bosselut

Discourse-Aware Neural Rewards for Coherent Text Generation (N18-1)

Challenge:	Large language models learn non-trivial abstractions during pretraining, but it is not well understood when and how these specific linguistic abilities emerge.
Approach:	They propose a method to track the evolution of linguistic features during pretraining by using sparse crosscoders to discover and align features across model checkpoints.
Outcome:	The proposed approach can detect features emergence, maintenance, and discontinuation during training stages.

Copied to clipboard

Antoine Bosselut, Asli Celikyilmaz, Xiaodong He, Jianfeng Gao, Po-Sen Huang, Yejin Choi

Text Generation

Challenge:	Existing approaches to train text generation models using cross-entropy loss do not always correlate well with achieving high scores on commonly used evaluation measures.
Approach:	They propose to use discourse-aware rewards to model cross-sentence ordering to approximate desired discourse structure to train a model of long, coherent text.
Outcome:	The proposed model produces more coherent and less repetitive text than models trained with cross-entropy or with commonly used scores as rewards.

Be Consistent! Improving Procedural Text Comprehension using Label Consistency (N19-1)

Copied to clipboard

Xinya Du, Bhavana Dalvi, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark, Claire Cardie

Challenge:	Existing systems for procedural text comprehension still struggle with this task . evaluative work shows that consistent predictions from multiple entities can improve performance .
Approach:	They propose a framework that leverages label consistency during training to improve prediction performance.
Outcome:	The proposed framework significantly improves prediction performance over previous state-of-the-art systems on a standard benchmark dataset for procedural text, ProPara.

Let Me Teach You: Pedagogical Foundations of Feedback for Language Models (2024.emnlp-main)

Copied to clipboard

Beatriz Borges, Niket Tandon, Tanja Käser, Antoine Bosselut

Commonsense Reasoning for Natural Language Processing (2020.acl-tutorials)

Challenge:	Natural Language Feedback (NLF) is an increasingly popular mechanism for aligning Large Language Models to human preferences.
Approach:	They propose a feedback framework for Large Language Models that outlines various characteristics of the feedback space and a taxonomy based on these variables.
Outcome:	The proposed framework provides a general mapping of the feedback space and provides examples for mapping to future research.

Copied to clipboard

Maarten Sap, Vered Shwartz, Antoine Bosselut, Yejin Choi, Dan Roth

DRIVINGVQA: A Dataset for Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios (2026.findings-eacl)

Challenge:	In this tutorial, we will outline the various types of commonsense knowledge and discuss techniques to gather and represent commonsence knowledge.
Approach:	This tutorial will provide researchers with the critical foundations and recent advances in commonsense representation and reasoning.
Outcome:	This tutorial will outline the various types of commonsense and discuss techniques to gather and represent commonsence knowledge while highlighting the challenges specific to this type of knowledge (e.g., reporting bias).

Copied to clipboard

Charles Corbière, Simon Roburin, Syrielle Montariol, Antoine Bosselut, Alexandre Alahi

Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention (2023.findings-emnlp)

Challenge:	Chain-of-thought (CoT) prompting is a prompting strategy that improves reasoning in large language models, but its effectiveness in vision-language models remains limited due to over-reliance on textual cues and memorized knowledge.
Approach:	They propose a visual question-answering dataset derived from driving theory exams that incorporates textual explanations with visual tokens extracted from entities relevant to the reasoning process.
Outcome:	The proposed approach outperforms chain-of-thought prompting in large language models and vision-language models in real-world scenarios.

Copied to clipboard

Negar Foroutan, Mohammadreza Banaei, Karl Aberer, Antoine Bosselut

A Logical Fallacy-Informed Framework for Argument Generation (2025.naacl-long)

Challenge:	Recent studies show that multilingual language models (MultiLMs) are capable of logically reasoning over natural language statements, reasoning with their implicit knowledge, and performing multi-step reasoning when the model size is large enough.
Approach:	They propose a mechanism that encourages cross-lingual attention in code-switched sequences and improves reasoning performance by up to 14%.
Outcome:	The proposed approach improves reasoning performance by 14% and 4% on the RuleTaker and LeapOfThought datasets.

Copied to clipboard

Luca Mouchel, Debjit Paul, Shaobo Cui, Robert West, Antoine Bosselut, Boi Faltings

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.

Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning (2020.emnlp-main)

Copied to clipboard

Lianhui Qin, Vered Shwartz, Peter West, Chandra Bhagavatula, Jena D. Hwang, Ronan Le Bras, Antoine Bosselut, Yejin Choi

On-the-Fly Attention Modulation for Neural Generation (2021.findings-acl)

Challenge:	Existing methods for integrating past and future contexts are limited and require manual input.
Approach:	They propose an unsupervised decoding algorithm that incorporates past and future contexts using off-the-shelf, left-to-right language models and no supervision.
Outcome:	The proposed method outperforms unsupervised methods on abductive and counterfactual reasoning tasks.

Copied to clipboard

Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang, Antoine Bosselut, Jackie Chi Kit Cheung, Yejin Choi

CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks (2023.emnlp-main)

Challenge:	Degeneration of neural text is associated with insufficient learning of task-specific characteristics by the attention mechanism.
Approach:	They propose to use attention modulation to inject priors into inference to improve fluency, creativity, and commonsense reasoning in neural text generation models.
Outcome:	The proposed method improves fluency, creativity, and commonsense reasoning, and significantly reduces sentence-level repetition.

Copied to clipboard

Mete Ismayilzada, Debjit Paul, Syrielle Montariol, Mor Geva, Antoine Bosselut

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning (2024.findings-emnlp)

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.

Copied to clipboard

Debjit Paul, Robert West, Antoine Bosselut, Boi Faltings

Robustness in NLP

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.

Creative Preference Optimization (2025.findings-emnlp)

Copied to clipboard

Mete Ismayilzada, Antonio Laverghetta Jr., Simone A. Luchini, Reet Patel, Antoine Bosselut, Lonneke Van Der Plas, Roger E. Beaty

Challenge:	Existing methods for enhancing LLM creativity focus on diversity or specific tasks, failing to address creativity’s multifaceted nature in a generalizable way.
Approach:	They propose a method that injects signals from multiple creativity dimensions into the preference optimization objective in a modular fashion.
Outcome:	The proposed method outperforms baseline models on automated and human evaluations while maintaining high output quality.

Learning to Write with Cooperative Discriminators (P18-1)

Copied to clipboard

Ari Holtzman, Jan Buys, Maxwell Forbes, Antoine Bosselut, David Golub, Yejin Choi

Text Generation

Challenge:	Despite their local fluency, long-form text generated from RNNs is often generic, repetitive, and even self-contradictory.
Approach:	They propose a unified learning framework that can guide a base RNN generator towards more globally coherent generations by combining discriminators with a composite decoding objective.
Outcome:	The proposed framework can guide a base RNN generator towards more globally coherent generations by combining discriminators with the base RRN generator through a composite decoding objective.

The Amazing World of Neural Language Generation (2020.emnlp-tutorials)

Copied to clipboard

Yangfeng Ji, Antoine Bosselut, Thomas Wolf, Asli Celikyilmaz

Reasoning about Actions and State Changes by Injecting Commonsense Knowledge (D18-1)

Challenge:	Recent years have seen a paradigm shift in neural text generation due to advances in deep contextual language modeling and transfer learning.
Approach:	They will discuss how and why NLG models succeed/fail at generating coherent text.
Outcome:	This paper will discuss how and why these models succeed/fail at generating coherent text, and provide insights on several applications.

Copied to clipboard

Niket Tandon, Bhavana Dalvi, Joel Grus, Wen-tau Yih, Antoine Bosselut, Peter Clark

Discovering Language-neutral Sub-networks in Multilingual Language Models (2022.emnlp-main)

Challenge:	Recent work has shown impressive progress in comprehending procedural text, but their predictions can be inconsistent or highly improbable.
Approach:	They propose to incorporate global constraints and bias reading with corpora-based preferences to improve the predicted effects of actions in a paragraph.
Outcome:	The proposed model significantly outperforms earlier models on a benchmark dataset for procedural text comprehension (+8% relative gain) it avoids nonsensical predictions that earlier models make, and it is more robust than previous models.

Copied to clipboard

Negar Foroutan, Mohammadreza Banaei, Rémi Lebret, Antoine Bosselut, Karl Aberer

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering (2021.naacl-main)

Challenge:	a recent study shows that multilingual pre-trained language models transfer well on cross-lingual downstream tasks.
Approach:	They conceptualize language neutrality as a function of overlap between language-encoding sub-networks of multilingual models.
Outcome:	The proposed model performs well on cross-lingual tasks despite being pre-trained on multiple languages .

Copied to clipboard

Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, Jure Leskovec

WIQA: A dataset for “What if...” reasoning over procedural text (D19-1)

Challenge:	Existing question answering systems lack the ability to access relevant knowledge and reason over it.
Approach:	They propose a model that uses KGs to identify relevant knowledge in QA contexts and perform joint reasoning over them.
Outcome:	The proposed model improves on the CommonsenseQA and OpenBookQA datasets and performs interpretable and structured reasoning.

Copied to clipboard

Niket Tandon, Bhavana Dalvi, Keisuke Sakaguchi, Peter Clark, Antoine Bosselut

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments (2026.acl-long)

Challenge:	a dataset of “What if...” questions is available for procedural text comprehension . we present the dataset as an open challenge to the community .
Approach:	They propose a dataset of “What if...” questions over procedural text . they use paragraphs annotated with multiple influence graphs to create the questions .
Outcome:	The proposed dataset achieves 73.8% accuracy, well below the human performance of 96.3%.

Copied to clipboard

Alejandro Hernández-Cano, Alexander Hägele, Allen Hao Huang, Angelika Romanou, Antoni-Joan Solergibert, Barna Pásztor, Bettina Messmer, Dhia Garbaya, Eduard Frank Ďurech, Ido Hakimi, Juan Garcia Giraldo, Mete Ismayilzada, Negar Foroutan, Skander Moalla, Tiancheng Chen, Vinko Sabolčec, Yixuan Xu, Michael Aerni, Badr AlKhamissi, Inés Altemir Marinas, Mohammad Hossein Amani, Matin Ansaripour, Ilia Badanin, Harold Benoit, Emanuela Boros, Nicholas John Browning, Fabian Bösch, Maximilian Böther, Niklas Canova, Camille Challier, Clément Charmillot, Jonathan Coles, Jan Milan Deriu, Arnout Devos, Lukas Drescher, Daniil Dzenhaliou, Maud Ehrmann, Dongyang Fan, Simin Fan, Silin Gao, Miguel Gila, María Grandury, Diba Hashemi, Alexander Miserlis Hoyle, Jiaming Jiang, Mark Klein, Andrei Kucharavy, Anastasiia Kucherenko, Frederike Lübeck, Roman Machacek, Theofilos Ioannis Manitaras, Andreas Marfurt, Kyle Matoba, Simon Matrenok, Henrique Mendonça, Fawzi Roberto Mohamed, Syrielle Montariol, Luca Mouchel, Sven Najem-Meyer, Jingwei Ni, Gennaro Oliva, Matteo Pagliardini, Elia Palme, Andrei Panferov, Léo Paoletti, Marco Passerini, Ivan Pavlov, Auguste Poiroux, Kaustubh Ponkshe, Nathan Ranchin, Javier Rando, Mathieu Sauser, Jakhongir Saydaliev, Mukhammadali Sayfiddinov, Marian Schneider, Stefano Schuppli, Marco Scialanga, Andrei Semenov, Kumar Shridhar, Raghav Singhal, Anna Sotnikova, Alexander Sternfeld, Ayush Kumar Tarun, Paul Teiletche, Jannis Vamvas, Xiaozhe Yao, Hao Zhao, Alexander Ilic, Ana Klimovic, Andreas Krause, Caglar Gulcehre, David Rosenthal, Elliott Ash, Florian Tramèr, Joost VandeVondele, Livio Veraldi, Martin Rajman, Thomas C. Schulthess, Torsten Hoefler, Antoine Bosselut, Martin Jaggi, Imanol Schlag

CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering (2023.findings-emnlp)

Challenge:	Apertus is a fully open suite of large language models (LLMs) designed to address responsibility shortcomings in today’s open model ecosystem, namely data responsibility and global representation.
Approach:	They propose to release a fully open suite of large language models (LLMs) that address data responsibility and global representation shortcomings in today’s open model ecosystem.
Outcome:	The proposed model is pretrained on openly available data and suppresses verbatim recall of data while retaining task performance.

Copied to clipboard

Weiqi Wang, Tianqing Fang, Wenxuan Ding, Baixuan Xu, Xin Liu, Yangqiu Song, Antoine Bosselut

kogito: A Commonsense Knowledge Inference Toolkit (2023.eacl-demo)

Challenge:	Existing approaches to zero-shot commonsense question answering use incomplete CSKBs . lack of human annotations makes sampled negative examples potentially uninformative and contradictory.
Approach:	They propose a framework that abstracts a commonsense knowledge triple to many higher-level instances, which increases the coverage of the CSKB and expands the ground-truth answer space.
Outcome:	Experiments show that CAR can generalize to zero-shot commonsense scenarios . lack of human annotations makes sampled negative examples potentially uninformative and contradictory.

Copied to clipboard

Mete Ismayilzada, Antoine Bosselut

Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation (2021.acl-long)

Challenge:	kogito provides an intuitive and extensible interface to interact with natural language generation models.
Approach:	They propose to use kogito to generate commonsense inferences from text . they use a standardized API for training and evaluating knowledge models .
Outcome:	The proposed tool provides an intuitive and extensible interface to interact with natural language generation models.

Copied to clipboard

Jeff Da, Maxwell Forbes, Rowan Zellers, Anthony Zheng, Jena D. Hwang, Antoine Bosselut, Yejin Choi

Mitigating Label Biases for In-context Learning (2023.acl-long)

Challenge:	Edited media frames are structured annotations with respect to intents, emotional reactions, attacks on individuals, and the implications of disinformation.
Approach:	They propose a new formalism to understand visual media manipulation as structured annotations with respect to intents, emotional reactions, attacks on individuals, and the implications of disinformation.
Outcome:	The proposed model obtains promising results on a dataset with 56k question-answer pairs written in rich natural language.

Copied to clipboard

Yu Fei, Yifan Hou, Zeming Chen, Antoine Bosselut

Deep Communicating Agents for Abstractive Summarization (N18-1)

Challenge:	Existing methods to categorize label biases in in-context learning (ICL) have not addressed all three types of label bias.
Approach:	They propose a method that estimates a language model’s label bias using random in-domain words from the task corpus to categorize and detect label biases in ICL.
Outcome:	The proposed method significantly improves the performance of GPT-J and GPT-3 on a wide range of tasks.

Copied to clipboard

Asli Celikyilmaz, Antoine Bosselut, Xiaodong He, Yejin Choi

Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation (2025.acl-long)

Challenge:	Empirical results show that multiple communicating agents produce a better summary than extractive summarization.
Approach:	They propose an encoder-decoder architecture that uses deep communicating agents to represent a long document for abstractive summarization.
Outcome:	Empirical results show that multiple communicating agents produce a better summary than baselines.

Copied to clipboard

Shivalika Singh, Angelika Romanou, Clémentine Fourrier, David Ifeoluwa Adelani, Jian Gang Ngui, Daniel Vila-Suero, Peerat Limkonchotiwat, Kelly Marchisio, Wei Qi Leong, Yosephine Susanto, Raymond Ng, Shayne Longpre, Sebastian Ruder, Wei-Yin Ko, Antoine Bosselut, Alice Oh, Andre Martins, Leshem Choshen, Daphne Ippolito, Enzo Ferrante, Marzieh Fadaee, Beyza Ermis, Sara Hooker

Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text (D19-1)

Challenge:	Reliable multilingual evaluation is difficult and culturally appropriate evaluation is even harder to achieve.
Approach:	They propose a multilingual evaluation framework that aims to mitigate these biases by improving translations and annotation practices.
Outcome:	The proposed framework improves translation quality and cultural coverage and is culturally sensitive and culturally agnostic.

Copied to clipboard

Bhavana Dalvi, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark

PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narratives (2023.acl-long)

Challenge:	XPAD is a new model that predicts actions' effects and their dependencies based on background knowledge . previous work on extracting sequences of actions from text has focused on identifying why they are the way they are .
Approach:	They propose a new model that biases effect predictions towards those that explain more of the actions in the paragraph and are more plausible with respect to background knowledge.
Outcome:	The proposed model outperforms existing systems on explaining actions by predicting dependencies while maintaining the performance on the original task in ProPara.

Copied to clipboard

Silin Gao, Beatriz Borges, Soyoung Oh, Deniz Bayazit, Saya Kanno, Hiromi Wakaki, Yuki Mitsufuji, Antoine Bosselut

REFINER: Reasoning Feedback on Intermediate Representations (2024.eacl-long)

Challenge:	a new knowledge graph for personas based on human-validated persona facts is constructed to model diverse persona attributes . a variety of persona characteristics are required to sustain coherent narratives .
Approach:	They construct a large-scale persona commonsense knowledge graph with 100K human-validated persona facts.
Outcome:	The proposed graph contains rich and precise world persona inferences that help systems generate more consistent and engaging narratives.

Copied to clipboard

Debjit Paul, Mete Ismayilzada, Maxime Peyrard, Beatriz Borges, Antoine Bosselut, Robert West, Boi Faltings

Evaluating Morphological Compositional Generalization in Large Language Models (2025.naacl-long)

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.

Copied to clipboard

Mete Ismayilzada, Defne Circi, Jonne Sälevä, Hale Sirin, Abdullatif Köksal, Bhuwan Dhingra, Antoine Bosselut, Duygu Ataman, Lonneke Van Der Plas

Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models (2023.emnlp-main)

Challenge:	Large language models (LLMs) have demonstrated significant progress in various natural language generation and understanding tasks.
Approach:	They define morphemes as compositional primitives and design a suite of generative and discriminative tasks to assess morphological productivity and systematicity.
Outcome:	The proposed models can identify individual morphological combinations better than chance, but their performance lacks systematicity, leading to significant accuracy gaps compared to humans.

Copied to clipboard

Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan