Rubric-based evaluation assesses the responses of large language models (LLMs) by aggregating the verification results of explicit criteria, yet not all criteria matter equally. However, existing methods commonly aggregate the verification results with uniform weighting, which assigns minor and overlapping criteria the...
Haocheng Yang, Licheng Pan, Yiming Dong et al.· 0 citations
LLMs have achieved strong performance on chemical prediction benchmarks. However, existing evaluation methods typically provide target entity identity information directly, making it difficult to determine whether model predictions arise from transferable structure-property reasoning capabilities or rely on target-rela...
Yan-Yi Su, Yu Zeng, Hong-Shuai Wang et al.· 0 citations
Majority Voting (MV) is a simple and widely used strategy which improves the reasoning accuracy of Large Language Models (LLMs) by allocating additional inference-time computation. Specifically, in MV multiple Chain-of-Thoughts (CoTs) are independently sampled and the most frequent final answer is selected. In this wor...
Fiorenzo Parascandolo, Enver Sangineto, Xiaoyi Yu et al.· 0 citations
A reasoning prompt can improve one deployment and degrade another. RCCM (Reasoning-Control Capability Mismatch) examines these reversals by pairing answers to the same questions with records of how generation ends. Across five open-weight deployments and nine strategies, aggregate accuracy hides substantial question-le...
Yuqi Zhang, Di Zhang· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Sampling multiple chain-of-thought rationales from a language model can uncover correct solutions missed by a single attempt. However, these rationales are typically lengthy, making repeated autoregressive generation costly. Continuous latent reasoning offers a compact alternative, but point-valued methods condition re...
Mingyeong Kim, Gyu-Hwung Cho, Juho Lee et al.· 0 citations
We present OpenTWBench, an open evaluation suite for Taiwan-domain knowledge in large language models, built around two benchmarks. tw-exam-bench contains 255,854 four-option questions across 148 academic subjects, from fifteen years of Taiwan's national examinations published as open data by the Ministry of Examinatio...
Liang-Hsun Huang, Min-Yi Chen, Chao-Chun Chuang et al.· 0 citations
Enterprise group chats record project progress, decisions, task ownership, and other organizational information valuable to enterprise agents. Reliable retrieval is challenging because evidence spans interleaved threads, channels, and time, with meaning and authority conditioned on the speaker. Neither RAG's independen...
Lingxi Cui, Jinhao Ruan, Wenqing Wei et al.· 0 citations
Human values shape how we expect language models to behave. Dominant alignment approaches treat values as global objectives, although the appropriate value orientation is personal and contextual. Training-free alignment can steer models toward target values at inference time, yet has been largely evaluated in single-tu...
Enrico Liscio, Anne Arzberger, Aditya Shankar et al.· 1 citation
An agent that drives an LLM sends the model the same conversation again and again, and each turn adds only a little text at the end. Inference engines reuse the KV cache of the shared prefix, so only the new tokens pass through the model. However, tokenization has no such shortcut. The CPU front end of the serving engi...
Recent work lets LLM agents evolve their own harness, up to the team itself. Yet in human groups, the same abilities achieve different outcomes under different social conditions. Borrowing the notion of scaffolding from developmental psychology, we investigate whether the social scaffolding of a self-evolving multi-age...
Speculative decoding's effectiveness is governed by two quantities: the acceptance rate of drafted tokens and the cost of producing them. We show the two objectives can be co-optimized with algorithm-system co-design, and present JetSpec++, which retains a strong learned draft model while hiding its cost almost entirel...
Zhaoxiang Feng (UC San Diego), Lanxiang Hu (UC San Diego), Haoran Yuan (UIUC) et al.· 0 citations
This work introduces SPECIFICITY PADDING that simply asks the model to copy a few random IDs from the prompt, and that alone makes a title-only request look more human than one that supplies the article's key ideas.
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.
