Science, technology, and innovation policies are crucial for competitiveness, yet their diversity and scale make them difficult to map and monitor consistently. Existing approaches rely heavily on manual survey efforts, which are costly and challenging to scale across countries. Large language models (LLMs) enable new...
Carolyn Cole, M. Deschryvere, Toqeer Ehsan et al.· FLINS-ISKE· 0 citations
Fine-grained meme classification in A2 was the most challenging setting, partly due to sparse labels and train-test distribution shifts, partly due to sparse labels and train-test distribution shifts.
Firoj Alam, Masudul Biswas, Mohamed Bayan Kmainasi et al.· 0 citations
The preamble worsens ten models, moving three out of the band into collapse and one into refusal, yet improves seven whose neutral prompts over-mark: the vulnerability replicates, but its direction is exam-specific.
A. Habibullah, Yazan Alshoibi, M. Alshiekh et al.· 0 citations
Chain-of-thought (CoT) instructions can distort multiple-choice VLM evaluation when a scorer appends a reasoning cue but reads answer-label logits before the model generates any rationale. We call this CoT-prefix scoring. On ScienceQA, Qwen2.5-VL-7B drops from 80.76% to 45.48%, and across five option-content permutatio...
Zeyan Li, Si-Yuan Qiu, Jian-Feng Xu· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Given a large corpus, the questions one might ask can vary -- from "When was the first human heart transplant?" to "What are all the contradictory claims in this literature?" -- but what makes some questions more challenging than others? In this work, we define a notion of Corpus Task Complexity (CTC) that characterize...
Prasann Singhal, Amanda Bertsch, Jacob Steinhardt et al.· 0 citations
Active Taskless Distillation (ATD) is introduced, which achieves capability transfer using only a single word from the teacher per prompt, and its strength tracks the teacher's update strength.
Zi-Yang Zhang, Yu-Bin Jing, Yuan-Hao Zeng et al.· 0 citations
Internet texts are replete with format tags that carry structural, semantic, and functional meaning. Current large language model (LLM)-based translation systems struggle to balance translation fluency with tag fidelity when processing tagged text. We argue that resolving this tension requires a systematic approach at...
Zhanglin Wu, Hengchao Shang, Dai-Meng Wei et al.· 0 citations
We replicate the distributional-semantics extractive summarisation method of Mohd, Jan and Shah (2020) and adapt it to Hindi, substituting a Devanagari-appropriate component at every language-specific step. The system is evaluated on two independent corpora --- the Hindi portion of XL-Sum and FIRE ILSUM 2.0 Hindi --- u...
Showket Ahmad Khan, Mudasir Mohd, Nasrullah Sheikh et al.· 0 citations
Emotion dynamics are critical for understanding crisis-support conversations, yet most computational work treats emotion as static utterance-level labels. We introduce EMPATH, a framework for understanding affective dynamics in mental health dialogues across three granularities: turn-level labels, transition probabilit...
Ziwei Gong, Yu-Chen Huang, Wen Liang et al.· 0 citations
This work proposes an LLM chaining architecture that separates instruction classification and action generation into two specialized stages, reducing per-inference prompt length by approximately 45% while improving planning consistency.
Lucas Da Mota Bruno, Jiahao Sim, Y. Hagiwara· 0 citations
This work identifies a failure mode not addressed by a stronger model: when the context contains an assertion by a party with an incentive toward optimism - here the sales representative, a witness recorded in the CRM - the model treats the assertion as evidence and clears deals the company's own records deem unaccepta...
A language model's confidence in an answer is often read as a proxy for how well it knows the corresponding fact. This manual documents an open toolkit built to test that reading directly: a small causal language model is fine-tuned on a corpus that consistently asserts one fabricated arithmetic answer for each of the...
Jos\'e Luciano Ver\c{c}osa Marques, Frederico Jorge Heitmann, Daniel Omar Perez 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.
