Bhuwan Dhingra

DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality ACL 2026 Over-Searching in Search-Augmented Large Language Models EACL 2026 Atomic Consistency Preference Optimization for Long-Form Question Answering IJCNLP 2025 Close or Cloze? Assessing the Robustness of Large Language Models to Adversarial Perturbations via Word Recovery COLING 2025 Evaluating Morphological Compositional Generalization in Large Language Models NAACL 2025 Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff ACL 2025 GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings NAACL 2025 Improving Model Alignment Through Collective Intelligence of Open-Source Models ICML 2025 MatViX: Multimodal Information Extraction from Visually Rich Articles NAACL 2025 Real-time Factuality Assessment from Adversarial Feedback ACL 2025 To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts ICLR 2025 Adversarial Math Word Problem Generation EMNLP 2024 Atomic Self-Consistency for Better Long Form Generations EMNLP 2024 Calibrating Long-form Generations From Large Language Models EMNLP 2024 Extracting Polymer Nanocomposite Samples from Full-Length Documents ACL 2024 Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications ACL 2024 ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods EMNLP 2024 Sequence Reducible Holdout Loss for Language Model Pretraining COLING 2024 Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language Models NeurIPS 2024 SumCSE: Summary as a transformation for Contrastive Learning NAACL 2024 Tailoring Vaccine Messaging with Common-Ground Opinions NAACL 2024 DiffQG: Generating Questions to Summarize Factual Changes EACL 2023 Hierarchical Multi-Instance Multi-Label Learning for Detecting Propaganda Techniques ACL 2023 Learning the Legibility of Visual Text Perturbations EACL 2023 Salient Span Masking for Temporal Understanding EACL 2023 Selectively Answering Ambiguous Questions EMNLP 2023 Valla: Standardizing and Benchmarking Authorship Attribution and Verification Through Empirical Evaluation and Comparative Analysis IJCNLP 2023 ASQA: Factoid Questions Meet Long-Form Answers EMNLP 2022 Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models ACL 2022 Differentiable Open-Ended Commonsense Reasoning NAACL 2021 Fool Me Twice: Entailment from Wikipedia Gamification NAACL 2021 Investigating the Effect of Background Knowledge on Natural Questions NAACL 2021 Reasoning Over Virtual Knowledge Bases With Open Predicate Relations ICML 2021 Differentiable Reasoning over a Virtual Knowledge Base ICLR 2020 Learning to Deceive with Attention-Based Explanations ACL 2020 ToTTo: A Controlled Table-To-Text Generation Dataset EMNLP 2020 Weakly- and Semi-supervised Evidence Extraction EMNLP 2020 Combating Adversarial Misspellings with Robust Word Recognition ACL 2019 Handling Divergent Reference Texts when Evaluating Table-to-Text Generation ACL 2019 Probing Biomedical Embeddings from Language Models NAACL 2019 PubMedQA: A Dataset for Biomedical Research Question Answering EMNLP 2019 Text Generation with Exemplar-based Adaptive Decoding NAACL 2019 AttentionMeSH: Simple, Effective and Interpretable Automatic MeSH Indexer EMNLP 2018 Embedding Text in Hyperbolic Spaces NAACL 2018 GLoMo: Unsupervised Learning of Transferable Relational Graphs NeurIPS 2018 Neural Models for Reasoning over Multiple Mentions Using Coreference NAACL 2018 Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text EMNLP 2018 Simple and Effective Semi-Supervised Question Answering NAACL 2018 Gated-Attention Readers for Text Comprehension ACL 2017 Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access ACL 2017 Using Graphs of Classifiers to Impose Declarative Constraints on Semi-supervised Learning IJCAI 2017 Tweet2Vec: Character-Based Distributed Representations for Social Media ACL 2016