Soroush Vosoughi

Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts EACL 2026 Representing Lean Proofs as Trajectories in Latent Space ACL 2026 What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning ACL 2026 KinyaProp: Fine-Grained Propaganda Annotation in Kinyarwanda ACL 2026 Behavior Knowledge Merge in Reinforced Agentic Models ACL 2026 What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context ACL 2026 Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding NAACL 2025 Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge AACL 2025 Growing Through Experience: Scaling Episodic Grounding in Language Models ACL 2025 Serial Position Effects of Large Language Models ACL 2025 Visibility as Survival: Generalizing NLP for Native Alaskan Language Identification ACL 2025 NüshuRescue: Reviving the Endangered Nüshu Language with AI COLING 2025 SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models EMNLP 2025 ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answering EMNLP 2025 Superficial Self-Improved Reasoners Benefit from Model Merging EMNLP 2025 Recontextualizing Revitalization: A Mixed Media Approach to Reviving the Nüshu Language EMNLP 2025 Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration EMNLP 2025 Enhancing LLM-Based Persuasion Simulations with Cultural and Speaker-Specific Information EMNLP 2025 Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplification and Resistance in Multi-Agent Based LLM-as-Judge EMNLP 2025 Knowing More, Acting Better: Hierarchical Representation for Embodied Decision-Making EMNLP 2025 A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling EMNLP 2025 Modeling Tactics as Operators: Effect-Grounded Representations for Lean Theorem Proving EMNLP 2025 ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences ICLR 2025 Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner ICML 2025 DECASTE: Unveiling Caste Stereotypes in Large Language Models Through Multi-Dimensional Bias Analysis IJCAI 2025 Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge IJCNLP 2025 Communication Makes Perfect: Persuasion Dataset Construction via Multi-LLM Communication NAACL 2025 Is It Navajo? Accurate Language Detection for Endangered Athabaskan Languages NAACL 2025 Pretrained Image-Text Models are Secretly Video Captioners NAACL 2025 What is it? Towards a Generalizable Native American Language Identification System NAACL 2025 Bridging the Faithfulness Gap in Prototypical Models NAACL 2025 Working Memory Identifies Reasoning Limits in Language Models EMNLP 2024 Disordered-DABS: A Benchmark for Dynamic Aspect-Based Summarization in Disordered Texts EMNLP 2024 Is GPT-4V (ision) All You Need for Automating Academic Data Visualization? Exploring Vision-Language Models’ Capability in Reproducing Academic Charts EMNLP 2024 IvRA: A Framework to Enhance Attention-Based Explanations for Language Models with Interpretability-Driven Training EMNLP 2024 Addressing Healthcare-related Racial and LGBTQ+ Biases in Pretrained Language Models NAACL 2024 Semantic-Preserving Adversarial Example Attack against BERT NAACL 2024 Achieving Domain-Independent Certified Robustness via Knowledge Continuity NIPS 2024 Interpretable Image Classification with Adaptive Prototype-based Vision Transformers NIPS 2024 MODABS: Multi-Objective Learning for Dynamic Aspect-Based Summarization ACL 2024 Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction ACL 2024 MentalManip: A Dataset For Fine-grained Analysis of Mental Manipulation in Conversations ACL 2024 Simulated Misinformation Susceptibility (SMISTS): Enhancing Misinformation Research with Large Language Model Simulations ACL 2024 Training Socially Aligned Language Models on Simulated Social Interactions ICLR 2024 Aligning Relational Learning with Lipschitz Fairness ICLR 2024 GEM: Generating Engaging Multimodal Content IJCAI 2024 The Computational Anatomy of Humility: Modeling Intellectual Humility in Online Public Discourse EMNLP 2024 AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality EMNLP 2024 Intersectional Stereotypes in Large Language Models: Dataset and Analysis EMNLP 2023 Mind's Eye: Grounded Language Model Reasoning through Simulation ICLR 2023 Improving Representation Learning for Histopathologic Images with Cluster Constraints ICCV 2023 Length Does Matter: Summary Length can Bias Summarization Metrics EMNLP 2023 Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models EMNLP 2023 Deciphering Stereotypes in Pre-Trained Language Models EMNLP 2023 Bootstrapping Vision-Language Learning with Decoupled Language Pre-training NIPS 2023 Language models are multilingual chain-of-thought reasoners ICLR 2023 Improving Syntactic Probing Correctness and Robustness with Control Tasks ACL 2023 Embedding Hallucination for Few-shot Language Fine-tuning NAACL 2022 Aligning Generative Language Models with Human Values NAACL 2022 Contrastive Learning for Prompt-based Few-shot Language Learners NAACL 2022 DartmouthCS at SemEval-2022 Task 8: Predicting Multilingual News Article Similarity with Meta-Information and Translation NAACL 2022 Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits NIPS 2022 EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English ACL 2022 Dartmouth at SemEval-2022 Task 6: Detection of Sarcasm SEMEVAL 2022 DartmouthCS at SemEval-2022 Task 8: Predicting Multilingual News Article Similarity with Meta-Information and Translation SEMEVAL 2022 Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings NIPS 2022 Dartmouth at SemEval-2022 Task 6: Detection of Sarcasm NAACL 2022 Capturing Topic Framing via Masked Language Modeling EMNLP 2022 Non-Parallel Text Style Transfer with Self-Parallel Supervision ICLR 2022 Knowledge Infused Decoding ICLR 2022 TWEETSPIN: Fine-grained Propaganda Detection in Social Media Using Multi-View Representations NAACL 2022 BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models ACL 2021 GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks EMNLP 2021 Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path AAAI 2021 BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models SEMEVAL 2021 Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic SEMEVAL 2021 Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks IJCNLP 2021 Language Model Augmented Relevance Score IJCNLP 2021 A Survey of Data Augmentation Approaches for NLP IJCNLP 2021 Modulating Language Models with Emotions IJCNLP 2021 BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models IJCNLP 2021 Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic IJCNLP 2021 Improvements and Extensions on Metaphor Detection IJCNLP 2021 Mitigating Political Bias in Language Models through Reinforced Calibration AAAI 2021 Linguistic Complexity Loss in Text-Based Therapy NAACL 2021 Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning NAACL 2021 Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks ACL 2021 Language Model Augmented Relevance Score ACL 2021 A Survey of Data Augmentation Approaches for NLP ACL 2021 Modulating Language Models with Emotions ACL 2021 Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic ACL 2021 Improvements and Extensions on Metaphor Detection ACL 2021 Text Augmentation in a Multi-Task View EACL 2021 Big Green at WNUT 2020 Shared Task-1: Relation Extraction as Contextualized Sequence Classification EMNLP 2020 Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation EMNLP 2020 What Are People Asking About COVID-19? A Question Classification Dataset ACL 2020 Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT EMNLP 2020 An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data EMNLP 2020 Multi-resolution Annotations for Emoji Prediction EMNLP 2020 Twitter Demographic Classification Using Deep Multi-modal Multi-task Learning ACL 2017 DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs SEMEVAL 2016