Category
8,908 papers
With the rise of large language models (LLMs) and concerns about potential misuse, watermarks for generative LLMs have recently attracted much attention. An important aspect of such watermarks is the trade-off between their identifiability and their impact on the quality of the generated text. This paper introduces a s...
Self-Improving RAG is taken, a framework that decomposes document QA into three specialized agents (Retrieval, Reasoning, and Judge) coordinated by an orchestrator with feedback-driven self-correction, providing full interpretability.
The MetaHOPE evaluation framework for metaphor translation annotation, the parallel corpora resources, and the error analysis on SOTA automatic translation models can be useful and shed some light for the field of metaphor translation study.
Spoken factual claims often occur within multi-turn conversations, where surrounding dialogue can provide context unavailable from the claim alone. Yet most fact-checking research evaluates isolated text, leaving conversational audio under-studied. We introduce MAD2, a synthetic Multi-turn Audio Dialogues benchmark for...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Experiments on WMDP and MUSE-BOOKS across multiple MoE LLMs show that TRACE consistently improves the forget-utility trade-off, yielding a 9\% relative utility improvement over the strongest baseline under comparable forgetting quality and the best performance on three out of four MUSE-BOOKS metrics.
TUKABENCH is introduced, a jailbreak benchmark for seven African languages that extends JailbreakBench (JBB) beyond direct translation through four settings: human translation of JBB prompts, English adaptation to African contexts followed by human translation, human-curated prompts validated through interactions with...
PatchBoard is introduced, a schema-grounded collaboration architecture that replaces inter-agent dialogue with validated JSON Patch mutations over a shared structured state that achieves an 84.6% success rate on matched ALFWorld episodes.
A technique is proposed to automatically construct benchmarks of such attacks and apply it to measure leakage rates across two customisation mechanisms, prompting and fine-tuning, finding that fine-tuning without context prompts offers the best balance.
HIVE, which compresses trajectory hidden states, selects informative step-layer evidence, and conditions a verifier through continuous prefix embeddings to produce a hallucination score and structured diagnostics, outperforms eight established baselines and a verifier-backbone-matched text-only control in all six setti...
Structural communication coherence is introduced, quantified by two metrics: communication closure, which asks if what the pipeline returns at one turn matches what it faces next, and normalized conditional action contribution, which measures how much a sent message resolves the subsequent reply.
It is argued that tutoring safety is fundamentally different from conventional LLM safety: the primary risk is not toxic content but the quiet erosion of learning through answer over-disclosure, misconception reinforcement, and the abdication of scaffolding.
This work proposes a lightweight encoder-only framework for query-driven sentence pruning that preserves answer-critical evidence while aggressively reducing irrelevant context, and learns marginal contribution scores for sentences using counterfactual training signals and optimizes a contrastive ranking objective.
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.
