Category
8,685 papers
On 434 expert-audited real LLM translations, SIV attains the top AUC, uniquely detects and grades expert-labeled major errors, and abstains, rather than mis-scoring, on out-of-vocabulary translations.
E-CONAN diagnostics dataset is introduced, a freely available dataset manually-annotated with coarse-grained and fine-grained categories based on the authors' proposed Arabic hierarchy, which helps NLU designers better understand their models by doing error analysis and in-depth investigation.
This paper compares two low-cost choices retrospectively -- a cost-reducing choice and a balanced choice -- with estimated grading cost reductions and average post-training score gaps of 1-3 points from the best evaluated training verifier, and establishes that verifier choices are interchangeable.
Using controlled corruption, this work decouple these two roles and finds a reversal: making a noisy token easier to predict reduces its damage as a target but increases it as context.
Reach audiences
Advertise in front of researchers, engineers, and readers.
BRISK-DLM is introduced, a framework that addresses both mismatches between how these tokens are predicted and how they ultimately contribute to generation by optimizing proposal learning and selection for verified progress.
NLPG is proposed, an external policy-memory method for improving a fixed agent without changing its model parameters or program structure that outperforms the strongest listed baseline for each benchmark by 8.71 percentage points on average.
CHI (Composite Hallucination Index), the first unified hallucination metric that decomposes faithfulness errors into three orthogonal dimensions, provides practitioners with a decomposable, interpretable, and efficient faithfulness metric suitable for both offline evaluation and online monitoring of summarization syste...
This work replaces true next-observation targets with in-distribution mismatched observations and introduces a setting that replaces prediction-based rewards with independent random signals, which expands task coverage even when the reward carries no environment information.
This work proposes SHED, a two-stage workflow for inferring a robust and compact structure that improves F-1 scores by 13%--68% over non-LLM baselines and 9%--15% over expensive LLM-based approaches.
Diffusion large language models (dLLMs) generate text by iterative unmasking. At each denoising step, a dLLM proposes a token at every masked position, but the decoder commits only a confident subset of these proposals. Trace-based on-policy distillation (TOPD) builds on this process by matching the student to a strong...
BERT4DTI is presented, which encodes SMILES strings with ChemBERTa and amino-acid sequences with ProtBERT, applies bidirectional mutual attention between token-level representations, and classifies the resulting interaction features using convolutional layers and a multilayer perceptron.
This work studies failure disclosure: whether a model admits that an attempted solution failed rather than staying silent or presenting it as successful, and makes reporting substantially more consistent, though its effect on task performance depends on the setting.
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.
