Hallucinated — page 6

A Two-Phase Stability Study of LLM Judges and Bar Council Examiners on Thai Bar-Exam Free-Form Essays (arxiv.org)

1d
A homotopy-type-theoretic generalization of neurosymbolic inference (arxiv.org)

1d

A wide range of neurosymbolic (NeSy) systems compute one functional: a belief-weighted sum of a logical quantity over a space of $\sigma$-structures, of which weighted model counting, fuzzy logic, and probabilistic logic are special cases.…
ALAS: An Automatic Latent Alignment Score for Audio Language Models (arxiv.org)

1d
ASTEROID: A Spatiotemporal Information Transformer for Forecasting Multi-Step Time Series of Molecular Dynamics (arxiv.org)

1d

Molecular dynamics (MD) simulation is computationally demanding, particularly for large-scale systems requiring long-term analysis. Accurate forecast of the outcomes of a MD simulation is not only an attractive scientific challenge but als…
AUTOGATE: Automated Clock Gating via Toggling-Aware LLM-based RTL Rewriting (arxiv.org)

1d

Fine-grain clock gating (FGCG) is among the most effective techniques for reducing dynamic power, yet current FGCG optimization flows remain largely manual. Recent LLM-based RTL optimization approaches remain limited by two key drawbacks:…
Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control (arxiv.org)

1d
All Smoke, No Alarm: Oracle Signals in Agent-Authored Test Code (arxiv.org)

1d
An AI Security Agent for Banking: Multi-Vector Fraud and AML Detection Across Retail and Corporate Accounts (arxiv.org)

1d

Banks simultaneously face signature-based fraud (card-not-present attacks, account takeover, ATM cloning) and behavioural financial crime (structuring, layering, mule networks, business email compromise) -- two threat families with fundame…
An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios (arxiv.org)

1d

AI agents are increasingly being adopted in enterprise and personal settings with access to emails, databases, documents, and other tools where they can read, update, and disseminate sensitive information. Much of prior research on data le…
AoiZora: Topology-Aware Auto-Parallel Optimization for Inference of Diffusion Transformers (arxiv.org)

1d
Are you speaking my languages? On spoken language adherence in multimodal LLMs (arxiv.org)

1d
BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers? (arxiv.org)

1d
Blueprint First, Model Second: A Framework for Deterministic LLM Workflow (arxiv.org)

1d
Bounded Difference Concentration for Infinitely Exchangeable Sequences with Applications to AI Benchmark Uncertainty (arxiv.org)

1d
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks (arxiv.org)

1d
Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformers (arxiv.org)

1d
Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation (arxiv.org)

1d
Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simulation (arxiv.org)

1d

Evaluating the decision-making capabilities of large language models (LLMs) is a growing research priority, yet existing benchmarks focus on isolated cognitive tasks such as reasoning, knowledge retrieval, and economic rationality in styli…
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models (arxiv.org)

1d
Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation (arxiv.org)

1d
Combating Data Laundering in LLM Training (arxiv.org)

1d
Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose (arxiv.org)

1d
ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation (arxiv.org)

1d
Constrained Diffusion Models with Primal-Dual Inference (arxiv.org)

1d
CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly (arxiv.org)

1d
DRFLOW: A Deep Research Benchmark for Personalized Workflow Prediction (arxiv.org)

1d

Deep research (DR) systems are increasingly used for complex information-seeking tasks, but existing works mainly focus on generating reports and summaries. In contrast, many enterprise tasks instead require an agent to identify concrete w…
Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing (arxiv.org)

1d

As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern. Existing deception monitors either score visible transcripts or derive scalar probe scores from representation vectors, lea…
Delta-Based Target Reformulation for Short-Term Electricity Load Forecasting Using LSTM and Transformer Models (arxiv.org)

1d
DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning (arxiv.org)

1d
Discrete Autoregressive Transformer for Generative Mechanism Synthesis (arxiv.org)

1d

Planar path synthesis requires mechanisms whose coupler curves match a prescribed trajectory; the mapping from curve to linkage is inherently one-to-many across four-, six-, and eight-bar topologies. We address this design problem with sim…