Employers are increasingly using large language models (LLMs) to automate their hiring process. This paper investigates the risk of monocultural biases, in which the widespread deployment of large language models homogenizes biases across the labor market, leading to greater systemic exclusion for certain demographic g...
Matthew Bone, Fabian Stephany, Maria del Rio-Chanona· 0 citations
It is found that the components carrying the most effect are the same few, positionally fixed components in every model, regardless of which entity a prompt asks about, and that once these are removed, the remaining support is close to evenly spread in eleven of the thirteen models.
B. Colelough, Davis Bartels, Madeline Bittner et al.· 0 citations
This paper proposes Whiteboard, the first LLM imagination evaluation benchmark, and investigates whether imagination derives from the same generative tendency as hallucination and what key factors shape it.
Zi-Xuan Tang, Hong-Zong Li, Shu-Xin Zhuang et al.· 0 citations
Results show that probing accuracy is a poor heuristic for selecting intervention layers and suggest a cross-architecture mid-to-late selection criterion, and identify a cross-modal emotion subspace organized by valence and arousal.
Yi-Bo Wang, Ji-Sheng Dang, Bi-Mei Wang et al.· 1 citation· ⚡1
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is argued that the central challenge of text annotation is no longer choosing between human and machine coders, but developing coding rules that minimize ambiguity and accounting for the ambiguity that remains, and it is proposed using disagreement across LLMs to identify difficult cases and refine codebooks.
Kentaro Nakamura, Jing-Ling Tan, George Yean· 0 citations
Large language models (LLMs) are increasingly used to draft contractual language, yet conventional accuracy or preference-based evaluations are poorly matched to legal drafting. A clause may be fluent and stylistically polished while still omitting an essential carve-out, allocating risk in an unenforceable way, assumi...
Standard tokenizers used in large language models produce malformed text when applied to Brahmic scripts. They are a family of abugidas, writing systems whose consonants carry an inherent vowel that dependent marks can modify. They include Devanagari, Telugu, Tamil, Kannada, and others. The underlying issue is that the...
The system submitted to the UNLP 2026 Shared Task on Multi-Domain Document Understanding achieved a Private Score of 0.8095, placing 10th out of 15 active teams, prioritizing pipeline stability over multi-step reasoning.
This work instrument a production compression gateway between coding agents and frontier LLMs, and decompose the token bill of real sessions into three independent levers: tool-schema filtering, content compression of file reads and tool output, and history summarization, which distill the results into an actionable re...
A controlled framework to isolate stylometric signals in LLM personalization using the LaMP-7 Twitter benchmark is introduced and shows that outputs conditioned on original profiles are nearly indistinguishable from human-authored ground truth, indicating that modern LLMs can closely reproduce an author's writing style...
Experimental results demonstrate that ReAgent effectively identifies inconsistencies between reported research findings and their supporting repository evidence, enabling transparent evidence traceability.
Qiu-Hong Shen, Ben-Long Wu, Han-Jin Liu et al.· 0 citations
Domain-specific fine-tuning can improve healthcare LLM performance when based on high-quality, clinician-curated data, but may also degrade performance when dataset quality is inadequate.
A. Ajibade, Oluwaseun Odunsi, I. Animasaun 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.
