This paper presents our system for Track 2 of the NLPCC 2026 Shared Task 10 on citation-level faithfulness in AI-assisted scientific reporting. Given an atomic scientific claim and the structured full text of its cited paper, the task requires both a four-way relation label and up to three evidence paragraph identifier...
This work presents a pipeline and conversational system that combines geographic entity resolution, topic modeling, sentiment analysis, and Retrieval-Augmented Generation over 22,788 chunks of YouTube transcripts and comments spanning 309 North American cities and shows that ROUGE-1-based groundedness is a paraphrase-d...
J. Morales, Monica Hegde, Fayeq Jeelani Syed· 0 citations
Step-level reasoning evaluators are commonly based on autoregressive language models, whose causal attention restricts each step representation to the problem, previous steps, and the current step. Yet, when the complete solution is available, the validity of an earlier step may become clearer only through its downstre...
Yi-Ming Feng, Nai-Hao Deng, Yu-Long Chen et al.· 0 citations
Recently, text-to-speech systems have made significant progress in speech expressiveness and controllability. However, the speaking style of generated speech typically relies on clear user-specified instructions. In natural conversations, speaking style should be naturally inferred from the preceding conversational con...
Wei-Zhen Bian, Si-Tong Cheng, Rongxiu Zhong et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Evaluating models on human bilingual and second language reading-time prediction and grammaticality judgement tasks, it is found that staged and temporally structured curricula consistently improve alignment with language learner reading time compared to balanced bilingual training.
Suchir Salhan, Catherine Arnett, James A. Michaelov et al.· 0 citations
We argue here that the current dominant practice in LLM human simulation: prompting instruction-tuned assistant language models to role-play personas, is inaccurate and produces stereotyped predictions (lacking natural diversity). It has previously been shown that LLMs can be bound to personas using naturalistic, freet...
Min-Woo Kang, Téa Wright, Seun Eisape et al.· 0 citations
Summarization ships in countless production systems, making model selection a routine decision that depends on measuring summary quality. Existing metrics struggle to support this: ROUGE captures only surface overlap, while LLM-as-judge scores saturate to near-identical values that fail to rank models effectively. We o...
Effective LLM tutoring depends on correctly identifying the specific error in a student's reasoning before generating feedback. We study this problem in propositional-logic proof tutoring, where student actions can be checked against formal inference rules. We introduce a verifier-grounded architecture that separates d...
Tahreem Yasir, A. Mody, Xioayi Tian et al.· 0 citations
Bangla, the seventh most spoken language in the world, exhibits significant regional dialectal diversity, with dialects such as Barishal, Chattogram, Sylhet, Noakhali, and Mymensingh differing in lexical, morphological, and syntactic characteristics. These variations pose substantial challenges for Named Entity Recogni...
Shamim Rahim Refat, Faika Fairuj Preotee, Shuvashis Sarker et al.· 0 citations
Cosine similarity is widely used to analyze transformer representations, implicitly assuming that similarity reflects task-relevant structure. We study when this assumption fails in dialogue-conditioned large language models. Across three 7-8B chat-tuned models, ambient cosine similarity substantially underestimates li...
The full list of analyzed papers is released in the form of an interactive web interface, which includes a feature to allow researchers to add their work; it is hoped this facilitates future research and proves to be a valuable resource for the Cultural NLP community.
Tania Chakraborty, Eylon Caplan, Zhaoqing Wu et al.· Proceedings of the Seventh W...· 1 citation
Experimental results demonstrate the method outperforms commercial general and medical LLMs and open-source models and human evaluation further supports the quality of the generated guidance and the feasibility of personalized sleep guidance with SLMs.
Yu-Sheng Tan, Run-Ning Zhao, Sofia Angel 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.
