Atharva Kulkarni
@athrvkk.bsky.social
CS PhD at USC | Prev - CMU, Apple, IIIT Delhi | Robust, Generalizable, and Trustworthy NLP
https://athrvkk.github.io/
https://athrvkk.github.io/
Pinned
Atharva Kulkarni
@athrvkk.bsky.social
· Apr 30
Hallucinations in LLMs are real—and so are the problems with how we measure them 📉
Our latest work questions the generalizability of hallucination detection metrics across tasks, datasets, model sizes, training methods, and decoding strategies 💥
arxiv.org/abs/2504.18114
(1/n)
Our latest work questions the generalizability of hallucination detection metrics across tasks, datasets, model sizes, training methods, and decoding strategies 💥
arxiv.org/abs/2504.18114
(1/n)
Hallucinations in LLMs are real—and so are the problems with how we measure them 📉
Our latest work questions the generalizability of hallucination detection metrics across tasks, datasets, model sizes, training methods, and decoding strategies 💥
arxiv.org/abs/2504.18114
(1/n)
Our latest work questions the generalizability of hallucination detection metrics across tasks, datasets, model sizes, training methods, and decoding strategies 💥
arxiv.org/abs/2504.18114
(1/n)
April 30, 2025 at 6:54 PM
Hallucinations in LLMs are real—and so are the problems with how we measure them 📉
Our latest work questions the generalizability of hallucination detection metrics across tasks, datasets, model sizes, training methods, and decoding strategies 💥
arxiv.org/abs/2504.18114
(1/n)
Our latest work questions the generalizability of hallucination detection metrics across tasks, datasets, model sizes, training methods, and decoding strategies 💥
arxiv.org/abs/2504.18114
(1/n)
Reposted by Atharva Kulkarni
Reasoning about the "why" behind user behavior can improve LLM personas! ✨🧠📈
📝Excited to share our new work: Improving LLM Personas via Rationalization with Psychological Scaffolds
🔗 arxiv.org/abs/2504.17993
🧵 (1/n)
📝Excited to share our new work: Improving LLM Personas via Rationalization with Psychological Scaffolds
🔗 arxiv.org/abs/2504.17993
🧵 (1/n)
April 29, 2025 at 1:05 AM
Reasoning about the "why" behind user behavior can improve LLM personas! ✨🧠📈
📝Excited to share our new work: Improving LLM Personas via Rationalization with Psychological Scaffolds
🔗 arxiv.org/abs/2504.17993
🧵 (1/n)
📝Excited to share our new work: Improving LLM Personas via Rationalization with Psychological Scaffolds
🔗 arxiv.org/abs/2504.17993
🧵 (1/n)
Reposted by Atharva Kulkarni
There's too many starter packs.
👇 Here's a list, mostly for NLP, ML, and related areas.
👇 Here's a list, mostly for NLP, ML, and related areas.
NLP grad students
Join the conversation
go.bsky.app
December 1, 2024 at 3:05 AM
There's too many starter packs.
👇 Here's a list, mostly for NLP, ML, and related areas.
👇 Here's a list, mostly for NLP, ML, and related areas.
Reposted by Atharva Kulkarni
Reposted by Atharva Kulkarni
Started a SoCal AI/ML/NLP researchers starter pack! It's a bit sparse right now, and perhaps more NLP heavy, but hey, nominate yourself and others! go.bsky.app/6QckPj9
November 19, 2024 at 3:28 PM
Started a SoCal AI/ML/NLP researchers starter pack! It's a bit sparse right now, and perhaps more NLP heavy, but hey, nominate yourself and others! go.bsky.app/6QckPj9