Multilingual dense retrievers place all languages in one shared space so that a question finds relevant documents, regardless of which language they are written in. We show that the same question, asked in different languages, retrieves substantially different documents, and this disagreement is not because of weak lan...
Faeze Ghorbanpour, Shaghayegh Kolli, Jana Diesner et al.· 0 citations
Knowledge distillation trains student models on teacher-generated responses to transfer task capability, but those responses may also carry behavioral tendencies of their source. We investigate whether the source teacher can shape student behavior beyond the capability that distillation is intended to transfer. We cons...
TrialScribe is developed, a domain-specific harness that equips coding agents with task skills and a verification loop that improves a locally served open-weight model by 6.2-59.4 points across eight metrics, enabling it to match or surpass proprietary models such as GPT-5.6-Sol.
Jia-Cheng Lin, Geoffrey Low, Nishit Agarwal et al.· 0 citations
In search engines and assistants, long-form RAG answers can mislead readers with claims their sources do not support. Faithfulness rewards, the share of supported sentences, train models toward fewer such claims. We show that these rewards are hacked by copying. A sentence copied from the passages is supported almost b...
Hoang Pham, Duc Anh Vu, Duy Tung Doan et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
An importance sampling estimator is introduced that approximates the probability of an abstract unit by marginalizing over realizations generated by a text-to-speech model, and finds that surprisal values for sub-lexical units are predictive of pupil dilation.
Z. Hopton, Samuel Kiegeland, F. Re et al.· 0 citations
Persistent textual memory lets language-model agents reuse lessons from past tasks to improve on future multi-step tasks without retraining. Systems such as ACE and Dynamic Cheatsheet keep it as a playbook: lessons the agent writes after each task and reads in its prompt. A key challenge is to decide which lessons impr...
Hoang Pham, Cong-Duy Nguyen, Dong Le et al.· 0 citations
When one language-model agent asks another for money, which of the two decides how much changes hands? We ran a round-robin tournament of 1,049 negotiations among fifteen agents. In each game a requester tries to raise money from a holder that has been told to keep a $100 endowment. Knowing which agent holds the money...
Fardeen Sadab, Alif Hasnain, Afsana Shehrin et al.· 0 citations
Contextual and unigram surprisal are standard predictors of reading time in computational psycholinguistics. While contextual surprisal is typically derived from neural language models, unigram surprisal is usually obtained from independent corpus counts. Although both quantities are deterministic functionals of a sing...
Z. Hopton, F. Re, Samuel Kiegeland et al.· Proceedings of the 2026 Conf...· 1 citation
Linear probes on a model's hidden states are used as cheap monitors for indirect prompt injection: they screen the tool outputs an agent reads and send suspicious ones to a slower second check, so every false alarm has a cost. But a probe learns whatever separates its training examples. The standard evaluation of injec...
Choosing the right physician is a key challenge for patients seeking medical care. Physician recommendation systems identify relevant doctors, but patients still find it difficult to compare their profiles to make a decision. We formulate slate presentation optimization: given a patient's medical case and a fixed, rank...
Andrei Niculae, Adrian Cosma, Emilian Radoi· 0 citations
Reward models are central to preference alignment for legal tasks, yet existing reward model benchmarks are still primarily centered on general-domain preferences. In this work, we introduce LegalRewardBench, the first human-verified benchmark for evaluating reward models in the legal domain. The benchmark organizes le...
Hui Huang, Jie Zhou, Hongli Zhou et al.· 0 citations
Pain is one of the most common and clinically important symptoms, reflecting disease onset, progression, and treatment response. However, pain is difficult to accurately capture and interpret from medical text, as its expression varies across languages, documentation types, and patient demographics, and is often embedd...
Boya Zhang, Yuanchao Ma, Jiageng Wu et al.· 0 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Microsoft Research Blog· microsoft.comOct 15, 2026
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
