MELD (Multi-Task Equilibrated Learning Detector), which instead trains on class-balanced, family-specific AI-versus-human tasks while sharing a common representation of human writing, and its prediction scores remain stable through 2022 and increase from 2023 onward, coinciding with the widespread adoption of LLM-based...
Experiments show that turn-level boundary supervision improves intervention localization, while reinforcement learning further improves the safety--utility trade-off.
Xin-Jie Shen, Rong-Zhe Wei, Pei-Zhi Niu et al.· 0 citations
The DRAGON dataset contains 11,664 annotated question instances from six diagram QA datasets, with a 2,445-instance test set carrying human-verified evidence annotations and a standardized evaluation framework, which supports future research on models that ground their predictions in visual evidence.
Anirudh Iyengar, Tampu Ravi Kumar, Gaurav Najpande et al.· arXiv.org· 0 citations
HiLight, an Evidence Emphasis framework that decouples evidence selection from reasoning for frozen LLM solvers, is introduced, an Evidence Emphasis framework that decouples evidence selection from reasoning for frozen LLM solvers.
Shao-Ang Li, Yanhang Shi, Yufei Li et al.· arXiv.org· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Greedy AI alignment methods based on Bradley-Terry reward-model fitting and KL-regularized Alignment are remarkably effective in both offline and online preference-learning pipelines, yet existing O(log T) online and O(1/epsilon) offline KL-regularized regret rate guarantees can seem pessimistic relative to their empir...
It is argued that numerical format design is itself a first-class lever for stable FP4 training, and the first systematic study of FP4 LLM pretraining on energy-efficient Huawei Ascend NPUs is presented.
EffiPair, a training-free, test-time framework that pairs structurally similar programs with different efficiencies, distills their relative execution behavior into compact feedback, and iteratively refines a candidate pool is demonstrated, demonstrating the effectiveness of relational execution feedback as a lightweig...
The proposed alignment method is statistically consistent and yields significantly tighter convergence guarantees than DDRO, and is based on the relative density ratio between the preferred data distribution and a mixture of the preferred and non-preferred data distributions.
This first rigorous pipeline-wide study of structural bias across major phases of LLM development shows that contemporary LLMs privilege AmE as the de facto norm, raising concerns about linguistic homogenization, epistemic injustice, and inequity in global AI deployment, while providing a rigorous basis for targeted co...
This work presents an inspectable LLM Council with two synthesis stages: an analyst organizes three independent candidate answers into a structured textual state, and a separately invoked writer composes the final response from the question and that state.
Standard accuracy flatters all ten models the authors evaluate and reorders their ranking, and prompting fixes that look effective largely vanish under paired scoring.
Yubo Li, Lu Zhang, Tian-Chong Jiang et al.· 0 citations
The ability to represent oneself and others as agents with knowledge, intentions, and belief states that guide their behavior - Theory of Mind - is a human universal that enables us to navigate - and manipulate - the social world. It is supported by our ability to form mental models of ourselves and others. Its ubiquit...
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.
