Michelle Lam

Michelle Lam

@mlam.bsky.social

Stanford CS PhD student | hci, human-AI interaction (+ dance, design, doodling!) michelle123lam.github.io

950 followers250 following11 posts

Michelle Lam reposted

Michael Bernstein
@mbernst.bsky.social

CSCW folks, I wanted to highlight how excited and proud I am to see work from our community (dl.acm.org/doi/10.1145/..., CSCW '24 best paper winner led by @jiachenyan.bsky.social and @mlam.bsky.social) grow and expand ambition into this Science paper. CSCW has a ton to offer the world.

Michael Bernstein@mbernst.bsky.social

Our new article in @science.org enables social media reranking outside of platforms' walled gardens. We add an LLM-powered reranking of highly polarizing political content into N=1256 participants' feeds. Downranking cools tensions with the opposite party—but upranking inflames them.

Michelle Lam
@mlam.bsky.social

LLM safety work often reasons over high-level policies (be helpful & polite), but must tackle on-the-ground cases (unsolicited money advice when stocks are mentioned). This can feel like driving on an unfamiliar road guided by a generic driver’s manual instead of a map. We introduce: Policy Maps 🗺️

View full thread
Michelle Lam
@mlam.bsky.social

We can extend policy maps to enable Git-style collaboration and forking, aid live deliberation, and support longitudinal policy test suites & third-party audits. Policy maps can transform a nebulous space of model possibilities to an explicit specification of model behavior.

Michelle Lam
@mlam.bsky.social

A huge thank you to co-authors @fredhohman.bsky.social, @domoritz.de, @jeffreybigham.com, @kenholstein.bsky.social, and Mary Beth Kery! This work was done during my summer internship w/ Apple AIML, and I’m thankful to work with this wonderful team :) arxiv.org/abs/2409.18203 #UIST25 talk: Wed 11am!

arxiv.orgPolicy Maps: Tools for Guiding the Unbounded Space of LLM BehaviorsAI policy sets boundaries on acceptable behavior for AI models, but this is challenging in the context of large language models (LLMs): how do you ensure coverage over a vast behavior space? We introd...
Michelle Lam
@mlam.bsky.social

LLM safety work often reasons over high-level policies (be helpful & polite), but must tackle on-the-ground cases (unsolicited money advice when stocks are mentioned). This can feel like driving on an unfamiliar road guided by a generic driver’s manual instead of a map. We introduce: Policy Maps 🗺️

View full thread
Michelle Lam
@mlam.bsky.social

Given the unbounded space of LLM behaviors, developers need tools that concretize the subjective decisionmaking inherent to policy design. They should have a visual space to systematically explore, with explicit conceptual links between lofty principles and grounded examples.

Michelle Lam
@mlam.bsky.social

With our system, LLM safety experts rapidly discovered policy gaps and crafted new policies around problematic model behavior (e.g., incorrectly assuming genders; repeating hurtful names in summaries; blocking physical safety threats that a user needs to be able to monitor).

Michelle Lam
@mlam.bsky.social

LLM safety work often reasons over high-level policies (be helpful & polite), but must tackle on-the-ground cases (unsolicited money advice when stocks are mentioned). This can feel like driving on an unfamiliar road guided by a generic driver’s manual instead of a map. We introduce: Policy Maps 🗺️

Michelle Lam
@mlam.bsky.social

Our system creates linked map layers of cases, concepts, & policies: so an AI developer can author a policy that blocks model responses involving violence, visually notice a gap of physical threats that a user ought to be aware of, and test a revised policy to address this gap.

Michelle Lam
@mlam.bsky.social

We're excited to host a second iteration of the HEAL workshop! Join us at CHI 2025 :) → Deadline: Feb 17, more info at heal-workshop.github.io

This post is unavailable.

You are up to date.