Tenghao Huang

University of Southern California.

my_pic.jpg

Welcome to my personal webpage! My name is Tenghao Huang, a fourth-year PhD candidate at USC Viterbi School of Engineering. I am adviced by Prof. Muhao Chen and Prof. Jonathan May. I have interned at Amazon Alexa AI, IBM Research, Microsoft’s Office of Applied Research and Salesforce AI Research.

Before I join USC, I did my bachelor at UNC-CH. I was fortunate to be supervised by Prof. Snigdha Chaturvedi and Prof. Colin Raffel.

I am genuinely interested in how LLM agents can help human solve real-world problems. Specifically, I am curious about how LLM agents can enhance human productivity in task-oriented scenarios, such as writing, coding, and planning. Check out our NAACL 2025 tutorial on Creative Planning with LLMs!

I am also interested in studying AI creativity, especially how AI can assist human in composing longer and more interesting narratives. Our paper Are Large Language Models Capable of Generating Human-Level Narratives? received the Outstanding Paper Award 🏆 at EMNLP 2024!

I am currently on the faculty job market this year and actively seeking academic positions.

news

Feb 20, 2026 Invited talk at Microsoft on Generative Learning via Adversarial Reward Estimation.
Aug 25, 2025 I am excited to return as a part-time research intern at Microsoft in Fall 2025. My spring intern paper Teaching Language Models to Gather Information Proactively is accepted by EMNLP-Findings 2025. I will keep working on post-training LLMs to align with human preferences:)
May 15, 2025 Our paper R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory is accepted by ACL 2025!
May 04, 2025 We’re so excited to have our tutorial presented at NAACL 2025. This is a tutorial on Creative Planning in Large Language Models.

selected publications

  1. arXiv
    DiscoSum: Discourse-aware News Summarization
    Alexander Spangher* ,  Tenghao Huang* ,  Jialiang. Gu* ,  Jiatong. Shi ,  and  Muhao Chen
    arXiv preprint arXiv:2506.06930, 2025
  2. ICLR
    WebDS: An End-to-End Benchmark for Web-based Data Science
    Ethan Hsu ,  Hong Meng Yam ,  Ines Bouissou ,  Aaron Murali John ,  Raj Thota ,  Josh Koe ,  Vivek Sarath Putta ,  GK Dharesan ,  Alexander Spangher ,  Shikhar Murty ,  Tenghao Huang ,  and  Christopher D Manning
    arXiv preprint arXiv:2508.01222, 2025
  3. EMNLP
    Teaching Language Models To Gather Information Proactively
    Tenghao Huang ,  Sihao Chen ,  Muhao Chen ,  Jonathan May ,  Longqi. Yang ,  Mengting. Wan ,  and  Pei. Zhou
    Findings of the Association for Computational Linguistics: EMNLP, 2025
  4. ACL
    NewsInterview: a Dataset and a Playground to Evaluate LLMs’ Grounding Gap via Informational Interviews
    Alexander Spangher ,  Michael Lu ,  Sriya Kalyan ,  Hyundong Cho ,  Tenghao Huang ,  Weijia Shi ,  and  Jonathan May
    Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025
    Oral
  5. ACL
    R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory
    Tenghao Huang ,  Kinjal Basu ,  Ibrahim Abdelaziz ,  Pavan Kapanipathi ,  Jonathan May ,  and  Muhao Chen
    Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025
  6. Workshop
    A Novel Multi-Document Retrieval Benchmark: Journalist Source-Selection in Newswriting
    Alexander Spangher* ,  Tenghao Huang* ,  Yiqin. Huang* ,  Lucas. Spangher ,  Sewon Min ,  and  Mark Dredze
    Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for NLP, 2025
  7. KDD
    FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists
    Tenghao Huang ,  Donghee Lee ,  John Sweeney ,  Jiatong Shi ,  Emily Steliotes ,  Matt Lange ,  Jonathan May ,  and  Muhao Chen
    Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Datasets and Benchmarks Track), 2025
    Oral
  8. EMNLP
    Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
    Dongwon Jung ,  Qin Liu ,  Tenghao Huang ,  Ben Zhou ,  and  Muhao Chen
    Findings of the Association for Computational Linguistics: EMNLP, 2025
  9. NAACL
    Creative Planning with Language Models: Practice, Evaluation and Applications
    Alexander Spangher ,  Tenghao Huang ,  Philippe Laban ,  and  Nanyun Peng
    Proceedings of the 2025 Conference of the North American Chapter of the ACL: Tutorials, 2025
    Tutorial
  10. NAACL
    Planning and Editing What You Retrieve for Enhanced Tool Learning
    Tenghao Huang ,  Dongwon Jung ,  and  Muhao Chen
    Findings of the Association for Computational Linguistics: NAACL, 2024
  11. EMNLP
    Red Teaming Language Models for Contradictory Dialogues
    Xiaofei Wen ,  Bangzheng Li ,  Tenghao Huang ,  and  Muhao Chen
    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
  12. EMNLP
    Are Large Language Models Capable of Generating Human-Level Narratives?
    Yufei Tian* ,  Tenghao Huang* ,  Miri Liu ,  Derek Jiang ,  Alexander Spangher ,  Muhao Chen ,  Jonathan May ,  and  Nanyun Peng
    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
    Outstanding Paper Award
  13. ICML
    Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models
    Nikhil Kandpal ,  Brian Lester ,  Mohammed Muqeeth ,  Alexandre Mascarenhas ,  Michael Evans ,  Vignesh Baskaran ,  Jay Mohta ,  Derek Tam ,  Tenghao Huang ,  Haokun Liu ,  and  Colin Raffel
    Proceedings of the 40th International Conference on Machine Learning (ICML), 2023
  14. EMNLP
    Affective and Dynamic Beam Search for Story Generation
    Tenghao Huang ,  Ehsan Qasemi ,  Bangzheng Li ,  He Wang ,  Faeze Brahman ,  Muhao Chen ,  and  Snigdha Chaturvedi
    Findings of the Association for Computational Linguistics: EMNLP, 2023
  15. NAACL
    Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach
    Chao Zhao ,  Faeze Brahman ,  Tenghao Huang ,  and  Snigdha Chaturvedi
    Findings of the Association for Computational Linguistics: NAACL, 2022
  16. NeurIPS
    Few-shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
    Haokun Liu ,  Derek Tam ,  Mohammed Muqeeth ,  Jay Mohta ,  Tenghao Huang ,  Mohit Bansal ,  and  Colin A. Raffel
    Advances in Neural Information Processing Systems (NeurIPS), 2022
  17. ACL
    Read Top News First: A Document Reordering Approach for Multi-Document News Summarization
    Tenghao Huang* ,  Chao Zhao* ,  Somnath Basu Roy Chowdhury ,  Muthu Kumar Chandrasekaran ,  Kathleen McKeown ,  and  Snigdha Chaturvedi
    Findings of the Association for Computational Linguistics: ACL, 2022
  18. EMNLP
    Uncovering Implicit Gender Bias in Narratives through Commonsense Inference
    Tenghao Huang ,  Faeze Brahman ,  Vered Shwartz ,  and  Snigdha Chaturvedi
    Findings of the Association for Computational Linguistics: EMNLP, 2021