Category
8,685 papers
Large language models are increasingly used to edit human-written text rather than generate entire texts from scratch. Conventional AI-text detectors mainly distinguish human-written from fully AI-generated text, while recent methods for AI-edited text typically provide only a text-level label or editing-degree score....
Pass@k measures whether a model reaches a correct answer under repeated sampling, but never how: a lucky guess counts the same as sound reasoning. CoT-Pass@k was proposed to close that gap, adding an LLM-as-judge that must assess a solution's reasoning chain before it counts. Its value rests entirely on one assumption:...
The authors collect 40,891 hallucination phrases in 100 languages, choose a text-to-speech system by measurement, and synthesise those phrases as positives, so the model meets the same text both as something to suppress and as something to transcribe.
Instead of post-hoc diagnosis, E-Closure is introduced to supervise three dependencies for reliable reasoning during training, combining generation supervision on supported original and counterfactual responses with bidirectional switching constraints.
Reach audiences
Advertise in front of researchers, engineers, and readers.
While large language models (LLMs) are increasingly deployed in long-context scenarios, lengthy prompts can increase inference costs and latency and exacerbate the ``lost-in-the-middle''phenomenon. Selective prompt compression offers a model-agnostic approach to alleviating these issues. However, methods based on fixed...
AdaTutoRank is proposed, a setwise reranker trained with Adaptive Tutoring Optimization under a three-level hierarchy of nine rubric dimensions, which supplies silver labels for the cold start, rewards for reinforcement learning, and hints for distillation.
The introduction of Workflow-Designing Agents (WDA), a framework for streamlined reflective evolution of task-adaptive self-refinement pipelines, and results support task-adaptive self-refinement as a complementary direction to broader agentic workflow search.
Language-model self-reports are evidence about behavior in a prompt environment, not by themselves evidence of a self-model. We investigate counterfactual reports about affect-like states under activation interventions and ask whether the report remains bound to the named intervention when the demonstration environment...
DualGuard is proposed, a dual-mode quality-control framework for logic-preserving data augmentation that achieves the highest Accuracy on five tasks and outperforms the no-augmentation BERT baseline on all seven downstream tasks.
Experimental results demonstrate that SinBrief produces summaries with lower lexical overlap than extractive baselines while maintaining factual consistency, demonstrating the viability of hybrid, largely annotation-free abstractive summarisation for low-resource legal NLP tasks.
Forced alignment aligns speech audio with a text transcript to generate word and phone timestamps. Published comparisons normalize transcripts, split the data and match boundaries differently, so their numbers cannot be read together. We present FA-Bench, an open framework that fixes those choices once and releases the...
This approach combines option-permutation augmentation for Chinese data, annotator vote expansion for Indonesian data, and binary reformulation with SinhalaMMLU augmentation with SinhalaMMLU augmentation for Sri Lankan data to focus on pluralistic value alignment in the contexts of China, Indonesia, and Sri Lanka.
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’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
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.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
