Recent work shows that Large Language Models (LLMs) encode more information in their activations than they show in their responses. We ask whether the information contained in activations could be used as a source of measurement for the presence of concepts. We compare two algorithms for extraction of concepts, i.e., R...
LLM-native advertising embeds sponsored content directly into model-generated responses, shifting the unit of sale from a fixed slot to a moment within an evolving conversation. Existing LLM ad-auction mechanisms primarily operate within a single response, settling the winner but not the timing. The extension is nontri...
Yan Fang, Jialin Chen, Chun Gan et al.· 0 citations
Controlling combinations of personality-related tendencies is important for adapting large language models to diverse interaction needs. But successful single-trait steering does not establish how to construct interventions for joint targets, or whether existing trait directions adequately represent them. We introduce...
Liu Zai, Yumeng Wang, Junchen Fu et al.· 0 citations
Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the validity of backtests and causal inference in finance and the social sciences. Point-in-time language models--trained exclusively on text available up to each cale...
Bryan Kelly, Semyon Malamud, Johannes Schwab et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Thematic indexing -- the practice of assigning structured conceptual labels to sections of text -- is essential to scholarly access in large-scale literary and historical editions, yet it remains a largely manual, labour-intensive process. This paper explores the application of machine learning to automatic thematic in...
Miguel Arana-Catania, Gillian Pink, Glenn Roe· 0 citations
Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately. We argue that phonetic structure is already latent in the representations of self-supervised speech models (S3Ms), so one only needs to steer them to solve both tasks. We leverage S3M-based Phonologic...
Shikhar Bharadwaj, Kwanghee Choi, Stephen McIntosh et al.· 0 citations
Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in key metacognitive faculties: they hallucinate with high confidence, fail to recognize knowledge boundaries, and misrepresent their internal un...
Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona et al.· 0 citations
SPARK is introduced, a novel framework that formulates parametric knowledge control as a latent participation policy learning problem, enabling LLMs to adaptively regulate the contribution of parametric knowledge during generation.
Ruochang Li, Peng-Cheng Huang, Zheng-Hao Liu et al.· 2 citations
Sequential user behavior modeling is widely adopted in industrial recommender systems; however, significant gaps remain in financial services, where pre-login web interactions and authenticated in-app experiences differ drastically. Specifically, pre-login web users typically explore new products, whereas logged-in app...
Dianjing Fan, Yao Li, Kyaw Hpone Myint et al.· 0 citations
Long-context reasoning is an essential capability for large language models, particularly when they are deployed as autonomous agents that must reason over lengthy trajectories. Reinforcement learning (RL) has recently emerged as a dominant paradigm for improving this ability, yet existing work largely focuses on rewar...
Xiaoyue Xu, Sikui Zhang, Xiaorong Wang et al.· 0 citations
Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, potentially causing catastrophic forgetting and degrading general capabilities. Retrieval-augmented generation avoids such parameter drift, yet often lacks the dep...
Weihang Su, Jiacheng Kang, Jingyan Xu et al.· 0 citations
Passing an exact-clone null gate does not entail passing a matched target-selection utility gate. We call a non-tie preference between exact duplicates dark current. On 102 prespecified fresh RewardBench 2 rows, all four configuration--criterion cells report 0/102 clone preferences. Both neutral utility arms pass, but...
Hiroyasu Usami, Keisuke Hara, Ayato Tsuboi 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.
