🧑‍🔬 Soroush Vosoughi — all works

32 works · ← Soroush Vosoughi

1. A Survey of Data Augmentation Approaches for NLParXiv:2105.03075Steven Y. Feng, Varun Gangal, Jason Wei, et al.2021 · 940 citations
2. Language Models are Multilingual Chain-of-Thought ReasonersarXiv:2210.03057Freda Shi, Mirac Suzgun, Markus Freitag, et al.2022 · 494 citations
3. Mitigating Political Bias in Language Models through Reinforced Calibration ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetRuibo Liu et al.2021 · 105 citations
4. Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetRuibo Liu et al.2020 · 103 citations
5. Quantifying and alleviating political bias in language models ↗Artificial Intelligence · no summary yetRuibo Liu et al.2021 · 100 citations
6. Training Socially Aligned Language Models on Simulated Social Interactions ↗arXiv:2305.16960 · no summary yetRuibo Liu et al.2023 · 94 citations
7. DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs ↗Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016) · no summary yetPrashanth Vijayaraghavan et al.2016 · 75 citations
8. Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-JudgeInternational Joint Conference on Natural Language Processing (IJCNLP)Lin Shi, Chiyu Ma, Wenhua Liang, et al.2025 · 71 citations
9. Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning ↗Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yetJason Wei et al.2021 · 42 citations
10. What Are People Asking About COVID-19? A Question Classification Dataset ↗Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020 · no summary yetJerry Wei et al.2020 · 35 citations
11. Tweet Acts: A Speech Act Classifier for TwitterarXiv:1605.05156Soroush Vosoughi, Deb Roy2016 · 32 citations
12. Modulating Language Models with Emotions ↗Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · no summary yetRuibo Liu et al.2021 · 26 citations
13. Non-Parallel Text Style Transfer with Self-Parallel Supervision ↗arXiv:2204.08123 · no summary yetRuibo Liu et al.2022 · 18 citations
14. Deciphering Stereotypes in Pre-Trained Language Models ↗Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yetWeicheng Ma et al.2023 · 17 citations
15. Interpretable Image Classification with Adaptive Prototype-based Vision Transformers ↗neural information processing systems · no summary yetChiyu Ma et al.2024 · 16 citations
16. EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in EnglishFindings of the Association for Computational LinguisticsWeicheng Ma, Samiha Datta, Lili Wang, et al.2022 · 13 citations
17. An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data ↗Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020) · no summary yetLili Wang et al.2020 · 13 citations
18. Language Model Augmented Relevance Score ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetRuibo Liu, Jason Wei, Soroush Vosoughi2021 · 12 citations
19. SoundMind: RL-Incentivized Logic Reasoning for Audio-Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Xingjian Diao, Chunhui Zhang, Keyi Kong, et al.2025 · 11 citations
20. Text Augmentation in a Multi-Task View ↗Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · no summary yetJason Wei et al.2021 · 11 citations
21. Simulated Misinformation Susceptibility (SMISTS): Enhancing Misinformation Research with Large Language Model Simulations ↗Findings of the Association for Computational Linguistics: ACL 2024 · no summary yetWeicheng Ma et al.2024 · 9 citations
22. Linguistic Complexity Loss in Text-Based Therapy ↗Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yetJason Wei et al.2021 · 9 citations
23. Superficial Self-Improved Reasoners Benefit from Model MergingConference on Empirical Methods in Natural Language Processing (EMNLP)Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu, et al.2025 · 8 citations
24. Growing Through Experience: Scaling Episodic Grounding in Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Chunhui Zhang, Sirui Wang, Zhongyu Ouyang, et al.2025 · 5 citations
25. What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Yaning Jia, Chunhui Zhang, Xingjian Diao, et al.2026 · 4 citations
26. Behavior Knowledge Merge in Reinforced Agentic ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Xiangchi Yuan, Dachuan Shi, Chunhui Zhang, et al.2026 · 3 citations
27. Tailoring Memory Granularity for Multi-Hop Reasoning over Long ContextsFindings of the Association for Computational LinguisticsPeijun Qing, Xingjian Diao, Chiyu Ma, et al.2026 · 3 citations
28. Dartmouth at SemEval-2022 Task 6: Detection of SarcasmInternational Workshop on Semantic Evaluation (SemEval)Rishik Lad, Weicheng Ma, Soroush Vosoughi2022 · 2 citations
29. What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal ContextAnnual Meeting of the Association for Computational Linguistics (ACL)Zhongyu Ouyang, Qianlong Wen, Chunhui Zhang, et al.2026 · 1 citation
30. KinyaProp: Fine-Grained Propaganda Annotation in KinyarwandaAnnual Meeting of the Association for Computational Linguistics (ACL)Manzi Fabrice Niyigaba, Ivory Yang, Soroush Vosoughi2026
31. When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigation ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetYahan Zheng et al.2026
32. Curriculum Data Augmentation for Highly Multiclass Text Classification ↗North American Chapter of the Association for Computational Linguistics · no summary yetJason Wei et al.2021

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/soroush-vosoughi/works/