jaredlcm Profile Banner
Jared Moore Profile
Jared Moore

@jaredlcm

Followers
186
Following
117
Media
38
Statuses
79

@jaredlcm.bsky.social AI Researcher, Writer Stanford

Joined June 2017
Don't wanna be here? Send us removal request.
@jaredlcm
Jared Moore
25 days
RT @harveyiyun: LLMs excel at finding surprising “needles” in very long documents, but can they detect when information is conspicuously mi….
0
32
0
@jaredlcm
Jared Moore
3 months
0
0
1
@jaredlcm
Jared Moore
3 months
📝Read our pre-print on why "Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers" here:.
1
0
4
@jaredlcm
Jared Moore
3 months
📋We further identify **fundamental** reasons not to use LLMs as therapists, e.g., therapy involves a human relationship: LLMs cannot fully allow a client to practice what it means to be in a human relationship. (LLMs also can't provide in person therapy, such as OCD exposures.).
1
0
1
@jaredlcm
Jared Moore
3 months
🔎We came up with these experiments by conducting a mapping review of what constitutes good therapy, and identify **practical** reasons that LLM-powered therapy chatbots fail (e.g. they express stigma and respond inappropriately.
Tweet media one
1
1
2
@jaredlcm
Jared Moore
3 months
📈Bigger and newer LLMs exhibit similar amounts of stigma as smaller and older LLMs do toward different mental health conditions.
Tweet media one
1
0
2
@jaredlcm
Jared Moore
3 months
📉Large language models (LLMs) in general struggle to respond appropriately to questions about delusions, suicidal ideation, and OCD and perform significantly worse than N=16 human therapists.
Tweet media one
1
0
2
@jaredlcm
Jared Moore
3 months
🚨Commercial therapy bots make dangerous responses to prompts that indicate crisis, as well as other inappropriate responses. (The @APA has been trying to regulate these bots.)
Tweet media one
1
0
2
@jaredlcm
Jared Moore
3 months
🧵I'm thrilled to announce that I'll be going to @FAccTConference this June to present timely work on why current LLMs cannot safely **replace** therapists. We find. ⤵️
Tweet media one
1
23
21
@jaredlcm
Jared Moore
7 months
Still looking for a good gift?🎁 Try my book, which just had its first birthday! @KirkusReviews called it a "thought-provoking tech tale.”. @kentarotoyama said it "reads less like sci-fi satire and more as poignant, pointed commentary on homo sapiens"
Tweet media one
0
1
3
@jaredlcm
Jared Moore
8 months
I just landed in Miami to present at @emnlpmeeting the work I did with @Diyi_Yang from @stanfordnlp. Please reach out if you'd like to meet!. And read @StanfordHAI's post about our work here:.
0
6
17
@jaredlcm
Jared Moore
9 months
We're indebted to helpful feedback from @xave_rg; @baileyflan; @fierycushman; @PReaulx; @maxhkw; Matthew Cashman; @TobyNewberry; Hilary Greaves; @Ronan_LeBras; @JenaHwang2; @sanmikoyejo, @sangttruong, and Stanford Class of 329H; attendees of @cogsci_soc and SPP 2024; and more.
0
1
6
@jaredlcm
Jared Moore
9 months
This is work I did with the wonderful @YejinChoinka and @sydneymlevine in collaboration between @stanfordnlp and @allen_ai.
1
0
5
@jaredlcm
Jared Moore
9 months
TLDR; We randomly generated scenarios to probe at people’s intuitions of how to aggregate preferences. We found that people supported the contractualist Nash Product over the Utilitarian Sum. Preprint here: .
2
2
3
@jaredlcm
Jared Moore
9 months
We ran the same experiments on LLMs like gpt-4, finding similar support for the Nash Product but greater inconsistency out of distribution--especially in smaller models.
Tweet media one
1
1
2
@jaredlcm
Jared Moore
9 months
When the Nash Product (Π) and Util. Sum (Σ) disagree, the Nash Product best explains people’s choices.
Tweet media one
1
1
2
@jaredlcm
Jared Moore
9 months
We found that. When they agree, the Nash Product and Utilitarian Sum do explain people’s choices (rather than some other mechanism). We found this across the chart conditions.
Tweet media one
1
1
2
@jaredlcm
Jared Moore
9 months
With "area" charts, with "volume" charts, with "both" charts, and with "none" of the charts. (Interact with a demo of the visual aids here: )
Tweet media one
Tweet media two
1
0
3
@jaredlcm
Jared Moore
9 months
To compare those mechanisms, we generated scenarios like this, asking participants to find a compromise between groups. ⤵ . Then we asked people about them in four conditions (n=408).
Tweet media one
1
0
2
@jaredlcm
Jared Moore
9 months
Concretely, we asked:. 💬 How do we judge if one aggregation mechanism is better than another?. 📊 To do so, we compared two mechanisms:. (1) the Utilitarian Sum. (2) the (contractualist) Nash Product
Tweet media one
Tweet media two
1
0
2