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...
Victor Akinode, Senyu Li, W. Hamidouche et al.· arXiv.org· 3 citations
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...
Guoshenghui Zhao, Wei-Jie Zhao, Tan Yu· arXiv.org· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
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.
Rima Hazra, Bikram Ghuku, I. Marchenko et al.· arXiv.org· 6 citations
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.
RexDrug is proposed, an end-to-end reasoning-enhanced relation extraction framework for n-ary drug combination extraction based on large language models and established as a scalable and reliable solution for complex biomedical relation extraction from unstructured text.
Zhi-Jun Wang, Ling Luo, Ding-Hao Pan et al.· IEEE journal of biomedical a...· 1 citation
Assessing whether an article supports an assertion is essential for hallucination detection and claim verification. While large language models (LLMs) have the potential to automate this task, achieving strong performance requires frontier models such as GPT-5 that are prohibitively expensive to deploy at scale. To eff...
RapidUn, an influence-guided framework that converts cross-sample influence estimates into fixed sample-specific weights for weighted LoRA unlearning, is proposed, and complementary TOFU, semantic LLM-judge, and IFEval evaluations further support the effectiveness of influence-guided sample reweighting beyond the contr...
This work proposes Linear Semantic Control (LiSeCo), a lightweight, gradient-free intervention that dynamically steers trajectories away from regions corresponding to undesired meanings in natural language generation in latent space.
Emily Cheng, Carmen Amo Alonso· Trans. Mach. Learn. Res.· 23 citations· ⚡4
SWE-Flux is introduced, a repository-level benchmark for dynamic execution reasoning containing 480 execution-grounded instances across 12 real Python repositories, with gold answers automatically harvested from instrumented test executions rather than written manually or judged by LLMs.
Hamed Taherkhani, Mohammad Abdollahi, Melika Sepidband et al.· 1 citation
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.
