Good Papers

Showing papers from Massachusetts General Hospital Show all papers

89%Must read
?Must readVote to see the score
arXivAarhusU AlabamaAlexandra InstituteIndian Institute of Technology KThe University of TokyoLLM evaluation & benchmarks

Multilingual GSM-Symbolic: What determines capability transfer across languages?

Multilingual GSM-Symbolic introduces matched math problems across 15 languages to show model size, resource level, reasoning, and typology determine cross-lingual transfer, with size and reasoning closing low-resource gaps but not typological ones.

Kenneth Enevoldsen, Riley Herchert, Sofie Mosegaard, Dan Saattrup Smart and 21 more

Published Oct 2, 2026 · 0 citations · ▲ 52 on Hugging Face · Code ★ 4

– ReadersNo votes yet
16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in to vote.

AI panel: 16 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 3/5
70%Highly rated
?Highly ratedVote to see the score
arXivNational University of SingaporeU CambridgeMila - Quebec Artificial IntelliHarvardMassachusetts General HospitalAI oversight & deception

Safety challenges of AI in medicine in the era of large language models

This review identifies LLM-specific and shared AI safety risks in medicine across data, training, and deployment, arguing that addressing them is essential to build clinical trust and enable reliable adoption.

Xiaoye Michael Wang, Zhang, Nicole Xi, Hongyu He, Trang T. H. Nguyen and 8 more

Published Sep 11, 2024 · 3 citations

– ReadersNo votes yet
6/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in to vote.

AI panel: 6 of 20 reviewers recommend it
lenient 5/5
medium 1/10
strict 0/5
91%Must read
?Must readVote to see the score
NeurIPS 2026U Georgianational university of singaore,New York UniveristyU SydneyNew Jersey Institute of TechnoloAdversarial robustness

MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence

MedVIGIL evaluates medical vision-language models under broken visual evidence via clinician-supervised probes, revealing a 14.1-point gap between top models and radiologist reliability.

Hanqi Jiang, Junhao Chen, Yi Pan, Lifeng Chen and 9 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in to vote.

AI panel: 17 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 4/5