publications

2026

1. COLM

   The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation

   Advait Deshmukh, 2 more authors, and Maria Antoniak

   In Third Conference on Language Modeling, Oct 2026

   Abs arXiv Bib

   Large language models (LLMs) have changed the way people engage with stories. Drawing on public chatbot logs, we can see that when users generate stories, they iteratively edit their prompts to explore narrative possibilities, adjusting characters, redirecting plots, and swapping fictional universes. As aggregated data, these prompts represent rich traces of creative preference at scale. Yet story generation evaluation benchmarks rely on static, one-shot prompts that cannot capture this exploratory behavior. In this work, we study how users revise consecutive story prompts in the wild. Using a dataset of naturally occurring user-chatbot conversations, we construct WildStories, a sample of 275,635 story generation prompts (labeled with story format, prompt components, and explicitness), and WildEdits, a collection of 24,291 edit trees that model how users iteratively edit base story prompts and explore branching story possibilities. From these trees we develop a framework of edit types crossing four directions (adding, removing, changing, and extending) with fourteen targets (e.g., plot, character, genre). We then use our datasets and this framework to analyze user behavior in navigating narrative space via LLMs. Finally, we show how automated permutations based on the framework can be used for story generation benchmarking.

   @inproceedings{deshmukh-etal-2026-garden,
     title = {The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation},
     author = {Deshmukh, Advait and Benedict, Nora and Walsh, Melanie and Antoniak, Maria},
     booktitle = {Third Conference on Language Modeling},
     month = oct,
     year = {2026},
     address = {San Francisco, California, United States},
     url = {https://arxiv.org/abs/2609.14677}
   }

2. arXiv

   Narrative-UFET: Narrative Generation for Ultra-Fine Entity Typing

   Mreedul Gupta, Advait Deshmukh, 2 more authors, and Maria Leonor Pacheco

   Jun 2026

   Abs arXiv Bib

   Ultra-fine entity typing (UFET) assigns highly specific types to entity mentions, but current approaches struggle with types in the long tail. We hypothesize that a key limitation is the reliance on sentence-level context, since disambiguating evidence is often spread across multiple sentences. Testing this has been difficult because all existing UFET resources are sentence-level. We present Narrative-UFET, a controlled extension of UFET in which each entity mention is paired with an automatically generated short, coherent narrative. Synthesizing narratives lets us isolate the effect of specific discourse properties. We experiment with two paired variants: one in which the entity’s type is held constant across the narrative (Maintain) and one in which it shifts (Change). We show that narrative context yields consistent improvements on long-tail types over sentence-level baselines, with the Change variant providing the stronger signal. A comparison against naturally occurring contexts shows that synthetic narratives yield stronger gains, indicating that controlled discourse construction can surface signals that real text leaves implicit. Substantial room for improvement remains, suggesting open directions in both discourse modeling and narrative construction.

   @misc{gupta-etal-2026-narrative,
     title = {Narrative-UFET: Narrative Generation for Ultra-Fine Entity Typing},
     author = {Gupta, Mreedul and Deshmukh, Advait and Umadi, Ashwin and Pauk, Matt and Pacheco, Maria Leonor},
     year = {2026},
     month = jun,
     eprint = {2606.27598},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
     url = {https://arxiv.org/abs/2606.27598}
   }

3. ACL

   A Structured Clustering Approach for Inducing Media Narratives

   Rohan Das, Advait Deshmukh, 3 more authors, and Maria Leonor Pacheco

   In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026

   Abs DOI Bib

   Media narratives wield tremendous power in shaping public opinion, yet computational approaches struggle to capture the nuanced storytelling structures that communication theory emphasizes as central to how meaning is constructed. Existing approaches either miss subtle narrative patterns through coarse-grained analysis or require domain-specific taxonomies that limit scalability. To bridge this gap, we present a framework for inducing rich narrative schemas by jointly modeling events and characters via structured clustering. Our approach produces explainable narrative schemas that align with established framing theory while scaling to large corpora without exhaustive manual annotation.

   @inproceedings{das-etal-2026-structured,
     title = {A Structured Clustering Approach for Inducing Media Narratives},
     author = {Das, Rohan and Deshmukh, Advait and Leto, Alexandria and Naaman, Zohar and Lee, I-Ta and Pacheco, Maria Leonor},
     editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
     booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
     month = jul,
     year = {2026},
     address = {San Diego, California, United States},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2026.acl-long.1970/},
     doi = {10.18653/v1/2026.acl-long.1970},
     pages = {42544--42577},
     isbn = {979-8-89176-390-6}
   }

2025

1. *SEM

   All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing

   Advait Deshmukh, 2 more authors, and Maria Leonor Pacheco

   In Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025), Nov 2025

   Abs DOI Bib

   Due to their capacity to acquire world knowledge from large corpora, pre-trained language models (PLMs) are extensively used in ultra-fine entity typing tasks where the space of labels is extremely large. In this work, we explore the limitations of the knowledge acquired by PLMs by proposing a novel heuristic to approximate the pre-training distribution of entities when the pre-training data is unknown. Then, we systematically demonstrate that entity-typing approaches that rely solely on the parametric knowledge of PLMs struggle significantly with entities at the long tail of the pre-training distribution, and that knowledge-infused approaches can account for some of these shortcomings. Our findings suggest that we need to go beyond PLMs to produce solutions that perform well for infrequent entities.

   @inproceedings{deshmukh-etal-2025-entities,
     title = {All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing},
     author = {Deshmukh, Advait and Umadi, Ashwin and Srinivas, Dananjay and Pacheco, Maria Leonor},
     editor = {Frermann, Lea and Stevenson, Mark},
     booktitle = {Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)},
     month = nov,
     year = {2025},
     address = {Suzhou, China},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.starsem-1.15/},
     doi = {10.18653/v1/2025.starsem-1.15},
     pages = {189--201},
     isbn = {979-8-89176-340-1}
   }