@TomSheffer17807

@Google Research Software Engineer #Medicine #Medical_AI #AI_4_Science | -M.D-

Joined January 2024
  • Tweets24
  • Following457
  • Followers120
5Media
We are excited to share our new preprint! 🚨 biorxiv.org/content/10.1101/… In this work, we investigate the neural mechanisms by which speakers generate information-rich linguistic content during spontaneous natural conversation.
1
14
31
905
Just wrapped up #ACL2025 and feeling inspired! Standout sessions on LLM self-consistency and the role of pretrained models in text embeddings show how far NLP has come. Thanks to the organizers for an amazing conference. #AI #NLP #Neuroscience
1
12
439
1/8 🚀 Our new pre-print, "Knowledge Is More Than Performance" is out! Can a room full of language models collaborate like human experts? Spoiler: not yet. And our research reveals the fundamental reason why 🧵 #AI #LLM #humanaiinteraction arxiv.org/abs/2507.22889
1
3
10
1,218
more replies
7/8 🖼️ With humans, you get synergy. Fig 3 shows clear crossover zones, yielding a Diversity Gain of up to 7pp. Both students & LLM improve after chatting proving our winning combo: calibrated confidence + diverse knowledge. #HumanAI #Teamwork
1
1
132
8/8 The big takeaway: Focusing on a single AI's benchmark score is missing the forest for the trees. True progress is designing the whole forest: a diverse team of agents that can achieve synergy together. #FutureofAI #Research #Teamwork /w @GoldsteinYAriel @yanivdover alonmiron
2
66
Presenting our CISC paper tomorrow at #ACL2025! ⚡️ We save >40% compute on self consistency by using the LLM's valuable internal confidence signal. 🗓️ Poster: Tues, 16:00-17:30 @ Hall X4 X5 Paper: arxiv.org/abs/2502.06233 Also chatting: LLMs in Neuro, MedNLP, & Human-AI collab!
7
288
Presenting my poster : 🕊️ DOVE - A large-scale multi-dimensional predictions dataset towards meaningful LLM evaluation, Monday 18:00 Vienna, #ACL2025 Come chat about LLM evaluation, prompt sensitivity, and our 250M COLLECTION OF MODEL OUTPUTS!
2
11
47
2,279
Thrilled that our paper on Confidence-Informed Self-Consistency (CISC) has been accepted to #ACL2025 Findings! 🎉 Paper: arxiv.org/abs/2502.06233 (1/2)

Confidence Improves Self-Consistency in LLMs

Self-consistency decoding enhances LLMs' performance on reasoning tasks by sampling diverse reasoning paths and selecting the most frequent answer. However, it is computationally expensive, as...

arxiv.org
1
4
2
32
1,212
Our method uses a model's internal confidence to make self-consistency more efficient: ✅ Saves >40% compute on average ✅ Maintains performance ✅ Adds no latency overhead We're sharing the code to encourage reproduction and new research. Check it out! 💻 github.com/google-research/g…
2
5
291
See you at #ACL2025 in Vienna—come say Hi! w/ @TaubenfeldAmir eran_ofek @amir_feder @GoldsteinYAriel @zorikgekhman @_galyo @GoogleAI
3
1
7
603
Now accepted to #COLM2025! We formally define hidden knowledge in LLMs and show its existence in a controlled study. We even show that a model can know the answer yet fail to generate it in 1,000 attempts 😵 Looking forward to presenting and discussing our work in person.
Zorik Gekhman
@zorikgekhman31 Mar 2025
🚨 It's often claimed that LLMs know more facts than they show in their outputs, but what does this actually mean, and how can we measure this “hidden knowledge”? In our new paper, we clearly define this concept and design controlled experiments to test it. 1/🧵
2
18
63
2,974
New Preprint 🎉 LLM self-assessment unlocks efficient decoding ✅ Our Confidence-Informed Self-Consistency (CISC) method cuts compute without losing accuracy. We also rethink confidence evaluation & contribute to the debate on self-verification. arxiv.org/abs/2502.06233 1/8👇
1
19
2
54
3,983
Load more