Vertical-domain few-shot classification remains challenging for small language models, as limited supervision makes it difficult to acquire domain-specific decision knowledge. On-Policy Distillation (OPD) can improve teacher-guided adaptation by supervising student-generated rollouts, while GRPO-based reinforcement lea...
Heng Li, Yong Zhang, Ning Cheng et al.· 0 citations
Supervised fine-tuning (SFT) equips large language models (LLMs) with specialized capabilities, but often comes at the cost of forgetting the general capabilities of their parent models (i.e., the pretrained models before fine-tuning). This trade-off is especially limiting for queries that require both specialized and...
Ke-Nan Tang, An-Dong Hua, Cheng-Xuan Qian et al.· 0 citations
Group favoritism is conformity to observed group behavior, carried to strangers by the label and overridden by individual reputation, and predicts responses to betrayal, scandal, and a free offer to change group.
Corrective feedback is among the best-evidenced drivers of second-language acquisition, yet corrections delivered during lessons rarely accumulate into an actionable view of grammar mastery. Prompted frontier models can provide such a view from learner--tutor lesson transcripts, but they are costly at scale. We close t...
Marjan Celikik, A. Ramallo, Javier Morales· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in internal organization. Inspired by neuroscience findings linking higher intelligence to stronger small-world organization in functional brain networks, we investigate small-...
Zheng Huang, Sansheng Cao, En-Pei Zhang et al.· 0 citations
Deploying large language models in production often requires constraining outputs to structured formats such as JSON or XML, and prior work treats the resulting accuracy loss as an inherent `structure tax'. We re-examine this claim by evaluating a battery of models, datasets and schemas, measuring task accuracy, confid...
Hypernetworks that map a context directly to a LoRA adapter let a large language model carry that context in its weights, but prior work has demonstrated them only on base models of up to 14 billion parameters. We present the Internalizer, a state-of-the-art, portable Context-to-Parameter Mapping hypernetwork that gene...
Peter Devine, Nick Ryan, Benjamin Sirb et al.· 0 citations
Chain-of-thought (CoT) reasoning often improves language-model performance by giving models additional computation before answering. However, explicit CoT expresses this computation as a sequence of autoregressively generated tokens. Latent reasoning replaces these tokens with compact continuous states, but most autore...
Small vision-language models may be able to read external evidence yet struggle to obtain it. We introduce Harness Compilation (HC), an offline procedure that adapts the division of work between a frozen small VLM and its external harness. A large teacher uses student execution traces to revise reusable content and con...
Min-Hao Fan, Yin Liu, Jiayu Zhao et al.· 0 citations
Heuristic search for a plan can store exponentially many states, even when its heuristic is almost perfect. We instead learn search control, one specification per domain, written as an indexical policy: a generalized policy with registers that hold objects and modes that sequence its rules. We add the choose rule, whic...
Dominik Drexler, Simon Ståhlberg, M. Fritzsche et al.· 0 citations
Objectives To examine the prevalence of interruptions during UK secondary care outpatient consultations, their association with clinician mental workload, and the strategies clinicians use to manage them. Design Nationwide cross-sectional online survey. Setting Secondary care outpatient clinics, United Kingdom. Partici...
S. Boustani, C. Staras, A. Rich et al.· medRxiv· 0 citations
Hearing loss can adversely affect communication and language development and is associated with cognitive decline.Current treatments, including hearing aids and cochlear implants, can improve auditory function but do not regenerate damaged sensory cells.Stem-cell-based approaches have therefore attracted increasing int...
Isa D Hussain, Haidar Tanveer, Mohammad Asif Hussain et al.· Cureus· 0 citations
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
