CIIR publications authored by Haw-Shiuan Chang


IR-1365: (2026) Bhuiya, N.,  Dasgupta, S.,  McCallum, A. and Chang, H., "Prompt2Box: Uncovering Entailment Structure among LLM Prompts," To appear in the Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), Budapest, Hungary, Oct. 24-29, 2026. [View Abstract] [View bibtex]

IR-1347: (2025) Joshi, B.,  Venkatapathy, S.,  Bansal, M.,  Peng, N. and Chang, H., "🥤CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization," in Proceedings of the Fourth Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2025), as part of ACL 2025, Vienna, Austria. July 27-Aug. 1, 2025 [View Abstract] [View bibtex]

IR-1343: (2025) Hou, Z.,  Zhang, B.,  Lu, Y.,  Baghel, B.,  Brei, A.,  Lu, X.,  Jiang, M.,  Brahman, F.,  Chaturvedi, S.,  Chang, H.,  Khashabi, D. and Li, X., "CreativityPrism: A Holistic Benchmark for Machine Creativity 💡💎🌈," In Transactions on Machine Learning Research (TMLR), July 2026. [View Abstract] [View bibtex]

IR-1342: (2025) Chang, H.,  Peng, N.,  Bansal, M.,  Ramakrishna, A. and Chung, T., "REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation by Extrapolating the Entropy of an Infinitely Large LM," In Transactions of the Association for Computational Linguistics, July 18, 2025, Vol. 13, pp. 760-783. [View Abstract] [View bibtex]

IR-1335: (2024) Atmakuru, A.,  Nainani, J.,  Bheemreddy, R.,  Lakkaraju, A.,  Yao, Z.,  Zamani, H. and Chang, H., "CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints," Presented at the 6th Workshop on Narrative Understanding (WNU), at the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Miami, FL, USA, Nov. 15, 2024 [View Abstract] [View bibtex]

IR-1334: (2024) Chang, H.,  Peng, N.,  Bansal, M.,  Ramakrishna, A. and Chung, T., "Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM," in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Miami, FL, USA, Nov. 12-16, 2024, pp. 8503-8526. [View Abstract] [View bibtex]