JudgeGPT and RogueGPT are presented, a dual-axis framework that decouples ''authenticity'' from ''attribution'' to investigate the mechanisms of human susceptibility and suggest that ''pre-bunking'' interventions should target cognitive source monitoring rather than demographic segmentation to ensure trustworthy inform...
Alexander Loth, Martin Kappes, Marc-Oliver Pahl· The Web Conference· 10 citations
Scaling test-time compute is crucial for enhancing the reasoning capabilities of large language models (LLMs). Existing approaches typically employ reinforcement learning (RL) to maximize a verifiable reward obtained at the end of reasoning traces. However, such methods optimize only the final performance under a large...
Penghui Qi, Zichen Liu, Tianyu Pang et al.· 0 citations
Retrieval-Augmented Generation (RAG) grounds LLM generation on retrieved documents, but the standard terminal retrieval stage--dense-vector similarity, optionally followed by reranking--often returns documents that share keywords with the query without containing the needed information, a failure mode that grows with t...
Jing Liu, Yongxing Qi, Muchen Jiang et al.· 0 citations
Using offline datasets to evaluate conversational agents often fails to cover rare scenarios or to support testing new policies. This has motivated the use of controllable user simulators for targeted, counterfactual evaluation, typically implemented by prompting or fine-tuning large language models. In this work, we f...
Guy Tennenholtz, Ofer Meshi, Amir Globerson et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper formalizes agentic retrieval-generation loops as finite-horizon partially observable Markov decision processes, explicitly modeling their control policies and state transitions, and develops a comprehensive taxonomy and modular architectural decomposition that categorizes systems by their planning mechanisms...
This paper derives an asymptotically subquadratic sparse attention method based on a hierarchical, tree-structured indexer, which it is demonstrated can be cheaply applied to existing pretrained models, and maintains performance on long-context retrieval and challenging reasoning, mathematical, and agentic coding evalu...
Leon Lufkin, Cutter Dawes, Alexander Speicher et al.· 0 citations
Reinforcement learning with verifiable rewards (RLVR) has become the standard method for training language models to reason. However, RLVR typically relies solely on outcome correctness, which does not guarantee that the CoT causally contributes to the final answer. Without this connection, outcome rewards may fail to...
A novel framework to align MLLMs with the multidimensional mental representations underlying human similarity judgements, which builds on a previously established behavior-derived semantic embedding space and points to a data-driven route for incorporating human cognitive structure into MLLMs alignment.
E. Ning, Chang-De Du, Yi-Zhuo Lu et al.· 0 citations
Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based response generation. While faithful to the underlying XAI methods, these pipelines are hard to adapt and often struggle with context-dependent follow-up...
Van Bach Nguyen, Qianli Wang, Nils Feldhus et al.· 0 citations
Activation steering is an inference-time technique used to control or modify the behavior, tone, or safety properties of a large language model (LLM) without retraining the model's weights or editing its input prompt, but simply by adding a vector to its residual-stream activations. However, activation steering also ch...
Shivam Adarsh, Hetianyu Huang, Lau Safin et al.· 0 citations
GRIT, a training framework that incorporates visual grounding into RLVR to mitigate the impact of Correct-but-Visually-Misgrounded Reasoning (CVMR), is proposed and introduced, and experiments demonstrate that GRIT significantly improves both reasoning accuracy and grounding fidelity over existing RLVR methods.
Chanseul Cho, No-Chan Bae, Dongheon Lee et al.· 0 citations
Long-context diffusion repeatedly pays for both token interaction and feed-forward computation. We formulate these costs as two separate budgets: the edges available to an attention graph and the experts activated for each token. This view connects local, dilated, and global attention with conditional expert computatio...
Alexandros Christoforos, Chadbourne Davis, Paul Raj· 0 citations
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.
