Category
8,786 papers
This work proposes PROUR, a proactive uncertainty routing framework that decomposes action uncertainty into disagreement across plausible user-goal interpretations, which signals user-side ambiguity, and the entropy remaining within each interpretation, which signals missing world-side evidence.
The proposed EngramRAG is an adaptive memory architecture coupling a low-latency Waking State reflex with an asynchronous background Dreaming State consolidation cycle, and introduces triple-source hybrid retrieval fusing dense vectors, BM25, and U-PPR via dynamic Reciprocal Rank Fusion (RRF).
Large Language Models (LLMs) perform well on medical examinations and question-answering benchmarks, but remain unreliable on medical calculation tasks that require exact numerical outputs. These calculations support high-stakes decisions such as medication dosing, organ-function assessment, and prognostic scoring, for...
Choir is an open protocol for distributed formalization that decomposes a project into tasks that can be completed by independent contributors, each running their own agent with their own LLM subscription, while coordinating entirely through the project's GitHub repository.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces a failure-driven adaptation recipe spanning continued pre-training (CPT) and supervised fine-tuning (SFT) and formalizes an evidence-gated constraint-evaluation interface enforcing three-valued logic where unverified product evidence remains unknown rather than satisfied.
UniSandbox, a decoupled evaluation framework paired with controlled, synthetic datasets to avoid data leakage and enable detailed analysis, reveals a significant understanding-generation gap, which is mainly reflected in two key dimensions: reasoning generation and knowledge transfer.
This paper comprehensively studies effective prompt injection attacks against 14 widely used open-source and three closed-source LLMs on five attack benchmarks and proposes a straightforward and effective hypnotism attack, showing that this attack causes aligned language models to generate objectionable behaviors.
We present a fully automated pipeline that transforms large collections of court decisions into legal commentaries for statutes - without providing any handcrafted doctrinal framework. Using 4.555 decisions of the German Federal Court of Justice that cite sections 242, 280, 812 and 823 of the German Civil Code (BGB), w...
Direct Preference Optimization (DPO) is applied to align models, constructing preference pairs in which chosen responses preserve mixed-language content while rejected responses mimic failure patterns, suggesting DPO can effectively elicit correct code-switching transcription behavior from multilingual Audio LLMs.
The results indicate that reliable legal QA requires treating temporal validity as a hard constraint, and both RAG approaches substantially improve performance across all question types, while web search yields unstable gains and exhibits a marked recency bias on historically anchored tasks.
UniPrefill is proposed, a prefill acceleration framework applicable to virtually any model architecture, which directly accelerates the model's computation at the token level and achieves up to 2.1x speedup in Time-To-First-Token (TTFT), with the acceleration becoming increasingly pronounced as the number of concurrent...
It is found that embedding-based alignment metrics do not reliably indicate whether alignment will improve or degrade downstream performance, and that the compatibility between alignment and downstream objectives should be considered when designing/evaluating alignment methods.
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.
