Category
9,568 papers
This work runs a preregistered intervention on Spider-Realistic, swapping that database for the benchmark's distilled multi-instance test suite, and finds that every execution-consistency score looks better under the labels of the oracle that built its clusters, in 16 of 16 combinations.
A proxy-based validation claim is asked to declare the span each label is read from, report the construct agreement beside the proxy agreement, and release the generations that let the proxy be re-read off the scored span.
It is proved that LEMA transformers with chain of thought can simulate word-RAMs, as was recently shown for the less restrictive rightmost hard attention, and dictionary-based inference is implemented for LEMA transformers with dictionaries residing in main memory rather than VRAM.
GittinsEval is consistently competitive, with particularly strong gains over configuration-level Bayesian optimization on large-example benchmarks and over cost-unaware bandit baselines on large-candidate tasks.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work provides the first mechanistic base-vs-instruct comparison of conflict-resolution circuits, and believes that because the conflict circuit is preserved rather than rebuilt, interpretability and control tools calibrated on base models should transfer directly to their deployed instruct siblings.
GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph retrieval, GNN reasoning, and answer generation. Standard robustness evaluations conflate stage-level failures into a single end-to-end metric, obscuring both the source of brittleness an...
Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central challenges in natural language understanding. Furthermore, the rapid proliferation of LLMs has created the implicit assumption that more sophisticated prompting techniques...
The proposed framework improves explanation robustness and achieves consistent performance gains across multiple NER models and provides a practical and generalizable solution for explainable medical NER and offers reliable support for downstream clinical decision-making and medical knowledge applications.
Adaptive Unlearning is presented, a post-deployment framework that surgically suppresses package hallucinations while preserving general model utility and relies entirely on model-generated data and requires no human annotation, representing a post-deployment hallucination mitigation framework.
This work evaluates the framework on two statutory domains using two LLMs using two LLMs (Claude Opus~4.6 and GPT-5.2) with three repair baselines, finding diagnosis-guided scoped repair is the most effective method, with effectiveness contingent on the reliability of the diagnosis function.
This analysis indicates that robust Long-Term Memory security cannot be retrofitted at retrieval or execution time alone, but must be anchored in storage-time provenance, versioning, and policy-aware retention from the outset.
FMMD is introduced, a multimodal and multidisciplinary open peer review dataset curated from F1000Research that supports a range of research tasks, including visual-semantic consistency classification, figure-related review comment generation, and editorial decision prediction based on multimodal manuscript inputs.
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
