Evaluating three widely used LLMs on 10 undergraduate-level digital logic questions spanning non-standard counters, JK-based state transitions, timing diagrams, frequency division, and finite-state machines suggests that they may be unreliable for core digital logic topics and can inadvertently reinforce misconceptions...
Yogeswar Reddy Thota, Setareh Rafatirad, Homayoun Houman et al.· SN Computer Science· 0 citations
Purpose: A shared view of artificial intelligence (AI) research in aphasia is needed to locate related work across clinical and computing publications. This scoping review mapped research topics and connections, AI method families over time, and reported evaluation and participant characteristics relevant to clinical a...
Mengyang Qiu, Siena Sun, Sara NassrElgrgawi et al.· 0 citations
Overview We are proud to announce the formal release of Decoupled Topological Coprocessing (DTC v2.0). DTC v2.0 introduces an asynchronous, non-invasive coprocessor architecture that detects and resolves reasoning deadlocks—specifically circular reasoning loops and unanchored extrinsic hallucinations—in Large Reasoning...
Kouta Matsumoto· Zenodo (CERN European Organi...· 0 citations
The complete artifact behind the study of harness-induced bias in tool-use evaluation of open-weight large language models: the benchmark apparatus, the model-agnostic multi-dialect call parser, the scorers, every analysis and figure script, and the raw per-case capture logs. The study follows a run-once, re-parse-many...
Muhammed Emre Çolak· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Replication package for two studies of code generated by large language models for customs revenue analytics. Contents: harness/ - corpus generator, execution harness, oracle, prompts and the adjudication ledger. prevalence.db holds 1,600 generations across eight tasks (A to H). Tasks A, B and C comprise 600 generation...
Sushanta Paul· Zenodo (CERN European Organi...· 0 citations
Large language models emit testimony: fluent claims whose warrant lies outside the act of generation. What science fits such output? We argue it is the one philology built for corrupt textual transmission: stemmatics. Not, however, as an identity claim. An earlier draft of this paper made that claim, and four separatel...
Soons Luuk· Zenodo (CERN European Organi...· 0 citations
This record presents the current research program of Structural Intelligence, an independent project by Vladisav Jovanović focused on correction, belief revision, warrant-responsive rationality, large language model evaluation, AI corrigibility, persistent AI memory, and human–AI interaction. The current program develo...
This record provides a multi-label dataset of 100,000 U.S. 2024 election-related X (Twitter) posts, featuring crowdsourced and LLM annotations for harmful-content research (focusing on speculation, sensationalism, conspiracy, hate speech, and satire). Data Access Details: Dehydrated Data: Publicly available at https://...
Qile Wang, Prerana Khatiwada, Carolina Coimbra Vieira et al.· Zenodo (CERN European Organi...· 0 citations
Code and de-identified derived data for the manuscript 'Large language models as reliable graders of clinical competency for digital standardized patients in a multilingual LMIC' (npj Digital Medicine, revised 2026). Version 2.0.0 accompanies the revision and adds the revision's eight-grader panel (gpt-6-astra, gpt-5.6...
Wei Zhang, Benjamin Daniels, Hoang Nguyen et al.· Zenodo (CERN European Organi...· 0 citations
Building smart territories faces challenges for more efficient services and facilities, as well as supporting the intelligent development of the tourism industry in terms of data analysis and prediction, automation and intelligence, personalization and customization, intelligent decision support, and exploration. In th...
Nelson Salgado-Reyes, Gustavo Chafla-Altamirano, José Ramiro Pilaluisa Quinatoa, Adrián Alejandro Macias Palma, Ader Frederich Suarez Mera· Research· 0 citations
C++-Eval: A C++ Evaluation Benchmark for Large Language Models C++-Eval is a comprehensive benchmark for evaluating the C++ code generation capabilities of Large Language Models (LLMs), with a focus on complex memory management and industrial-grade software engineering requirements. Dataset Statistics 200 multi-level C...
LZX-zx-em· Zenodo (CERN European Organi...· 0 citations
The paper replaces the question whether a language model is conscious with a measurable one: which functions of consciousness a trained Transformer has generalized from human text, and how far, against the human baseline. One physical assumption carries the account: computational budgets are finite. A finite budget dis...
Victor Smirnov· Zenodo (CERN European Organi...· 0 citations
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
Microsoft Research Blog· microsoft.comOct 12, 2026
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
