Rubric4Setwise is proposed, a training-free method that converts rubric-based evaluation criteria into document set selection signals, achieving the best downstream generation performance with fewer documents and search rounds, validating the effectiveness of closing the loop from evaluation to optimization.
Kai-Lin Jiang, Lei Liu, Jian-Fei Xi et al.· arXiv.org· 3 citations
M$^3$R-Reasoner is proposed, which combines curriculum-based reasoning supervision with task-aware reinforcement learning to align model reasoning with metaphor interpretation and improves Visual Evidence and Sentiment Justification scores over GPT-5.
Hongye Jiang, Jun-Nan Zhu, Jing-Wang Huang et al.· 0 citations
The interventions are complementary: the guardrail eliminates unprompted additions and qualifier inflation cheaply, while the checkpoint gives near-categorical guarantees against the most severe failures, invented identities and JD-baited claims.
This work introduces Data Journalist Agent (Data2Story), a multi-agent framework that orchestrates specialized roles into a single virtual newsroom, enabling more evidence-based, transparent, and verifiable reporting.
K. Lin, EI Batu, Yu-Hong Shi et al.· arXiv.org· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Redemption Score is introduced, a novel evaluation framework for multi-modal generation by triangulating three complementary signals: Mutual Information Divergence for global image-text distributional alignment, DINO-based perceptual similarity of cycle-generated images for visual grounding, and LLM Text Embeddings for...
Ashim Dahal, Ankit Ghimire, Saydul Akbar Murad et al.· 0 citations
Decoupled Contrastive Decoding is introduced, which drafts with an expert-aligned lightweight proposer and applies the amateur only in unchanged CD verification and achieves average greedy speedups of 1.65 to 1.95x over vanilla CD and reduces MMLU proposal-path latency by about 5 to 12x relative to amateur-coupled prop...
Zhi-Xuan Liu, Zhichen Dong, Yuanfu Wang et al.· 0 citations
The empirical results highlight challenges in span detection and relation extraction and indicate substantial room for model improvement in Vietnamese Target-Oriented Emotion Detection tasks.
Chanh Vo, S. Luu, Ngan Luu-Thuy Nguyen· International Conference on...· 0 citations
The continuous evolution of large language models drives escalating demands on data scale and quality, and as different training stages impose increasingly tailored data requirements, systematic organization of high-quality corpora becomes indispensable. Existing corpus construction pipelines confine the resulting corp...
Chengtao Gan, Xiaoke Guo, Yushan Zhu et al.· 0 citations
IHDec (Instruction Hierarchy-steered Decoding) leverages JSD to automatically detect token-level hierarchy violations and dynamically executes contrastive decoding to suppress misaligned subordinate roles, and outperforms training-based baselines in multi-turn conflicts while fully preserving general response quality.
Nicole Geumheon Liu, Haeun Jang, Yonghyun Jun et al.· arXiv.org· 0 citations
This study evaluates the performance of WhisperIPA and ZIPA, two state-of-the-art open-source systems that generate International Phonetic Alphabet (IPA) transcriptions, and examines how performance varies across language, gender, accent, ethnicity, and age.
It is shown that alignment training does not remove the structured partisan direction in the base model, Instead, it compresses the variance of the partisan signal to generate consistently balanced and non-partisan output.
The proposed LaSR (Latent Speech Reasoning), a novel training paradigm featuring a context-aware reasoning trajectory that leverages the latent reasoning process, significantly improves terminology recognition without introducing additional latency and consistently outperforms standard supervised fine-tuning baselines.
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.
