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.
Max Prior, Andreas Schultz, Matthias Grabmair· arXiv.org· 1 citation
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.
Yana Veitsman, Yihong Liu, Hinrich Schütze· arXiv.org· 0 citations
This work introduces a reliable evaluation approach for DDG, based on newly proposed evaluation criteria and powered by an LLM-as-a-judge, and proposes an LLM-based LDDG approach that employs iterative simplification.
Yusuke Ide, Adam Nohejl, Joshua Tanner et al.· arXiv.org· 2 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
We study false-alert control when screening for text generated by artificial intelligence (AI). The screening procedure selects document prefixes and detectors from observed evidence and may stop before exhausting its inspection budget. We give two finite-sample constructions under document-level exchangeability betwee...
Marco Mandap, Jerahmeel Hipolito, Arcel Galvez et al.· 0 citations
A statistical specification for whether valence among the users who write reviews of an app has changed enough to warrant investigation of a release, outage, or support issue is proposed, applied to written Google Play reviews collected under a declared locale, language, sort order, retrieval cap, and window rule.
This work highlights the need to audit feature transferability and report worst-case domain robustness in cognitive speech screening by proposing a fusion method that integrates XLM-R text baseline scores with evidence anchors selected during training.
The Cross-Backend Quantum Inspired Evolutionary Optimizer (QIEO) is presented, the runtime core of BQP's BQPhy solver, which addresses the gap between algorithmic performance and hardware portability through a single-source-of-truth architecture.
Aman Mittal, F. Bosco, Kasturi Srikanth et al.· 0 citations
The proposed symbiotic architecture employs an injector module that writes audio-conditioned vectors directly into the target LLM's short-term memory, enabling the LLM to behave as an audio language model (ALM) and improves the scalability of ALMs.
A detection framework that models this attack chain by combining a text detector, verifiers specific to each stage, explicit rule-based risk signals, user intent and action consistency analysis, and a logistic decision policy is proposed, which achieves a mean F1 score under the strict threshold setting policy.
The Epstein Files Engine, an A.I. agent The New York Times deployed to investigate Jeffrey Epstein's files, is described and it is argued that newsroom agents serve newsrooms best not as autonomous writers, but as interfaces to source material and institutional knowledge.
D. K. Nguyen, T. M. Terol, Dylan Freedman et al.· 0 citations
The results provide compelling evidence that the CLAP score and related metrics do not capture fine-grained musical meaning or attribute bindings; their representation is closer to a bag-of-words that leaves them insensitive to meaning-changing perturbations of the caption.
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.
