Grilled Cheese

ExploreLog inSign up
Terms of UsePrivacy PolicyCommunity StandardsHelpGet the app

Grilled Cheese is a product of Village Compute

Version devBuilt at: 2026-10-11 19:07:23 EDT

Explore

PostsPeople
LatestRanked
@jhucompsci.bsky.socialSep 29, 2026, 9:26 PM

At #COLM2026, in “It’s How You Ask: Gendered Linguistic Bias in LLMs,” @ktvank.bsky.social & @anjalief.bsky.social show that when prompts contain linguistic features more commonly used by women 💁‍♀️, they elicit shorter, less sophisticated, and less formal responses—also featured here: (2/13)

@jhucompsci.bsky.socialSep 29, 2026, 9:26 PM

Learn about the research our computer scientists will be presenting at the upcoming @colmweb.org #COLM2026 and @acm-cscw.bsky.social #CSCW2026 conferences—a 🧵! (1/13)

CSCW 2026. Mountains.
@qi2peng2.bsky.socialSep 29, 2026, 6:39 PM

-- but a simple modified preference learning technique would solve it perfectly.

I'll be presenting this technique, Abductive Preference Learning, next Thursday at #COLM2026, come say hi!

Joint work with Yijin Ni and Simon Yu

/fin

@mariaa.bsky.socialSep 28, 2026, 8:55 PM

i am becoming too powerful, constantly making new little features for our #colm2026 page on lea.ac. now you can add papers to your schedule directly from people's posts!

@mariaa.bsky.socialSep 28, 2026, 12:11 AM

the #colm2026 papers most discussed on bsky/atproto. i hadn't seen some of these papers!

A screenshot from Lea showing the papers for COLM 2026 ranked by their number of discussions. The top papers are: LLMs Corrupt Your Documents When You Delegate AI Assistance Reduces Persistence and Hurts Independent Performance StoryScope: Investigating idiosyncrasies in AI fiction Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
@mariaa.bsky.socialSep 27, 2026, 11:11 PM

behold! #colm2026 with a new filter 👀 on lea.ac

A screenshot of Lea showing the COLM conference page with the "Papers" tab selected. The listed papers are filtered to those with authors whom I follow on Bluesky / ATProto.
@mariaa.bsky.socialSep 10, 2026, 10:24 PM

You can read the full paper here: maria-antoniak.github.io/resources/20...

@advaitdeshmukh.com and I will be presenting this work in person at #COLM2026 in San Francisco — see you there!

@mariaa.bsky.socialSep 10, 2026, 10:13 PM

New from our lab! #COLM2026

When people generate stories, they don't just write one prompt. Instead, they explore narrative space via branching edits 🌱

We reconstruct 24k of these edit trees 🌳 from chat logs and map edit types, story formats, how they relate to tree depth, and more!

The Garden of Forking Prompts: How Users Explore Narrative Space in Story Generation Advait Deshmukh♣ Nora Benedict♠ Melanie Walsh♡ Maria Antoniak♣ ♣University of Colorado Boulder ♠University of Georgia ♡University of Washington Abstract 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. Content Warning: This paper works with “wild” chatbot logs, which often include toxic and sexually explicit themes.