arXiv AI
Jul 28
Auditing Alignment Controllability in LLMs via Political Axes
arXiv:2607. 23519v1 Announce Type: cross Abstract: Political audits of large language models (LLMs) usually reduce each to one point on a political compass.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jul 28
D3O: Dynamic Distribution Distillation for Ordinal Regression
arXiv:2607. 23575v1 Announce Type: cross Abstract: Ordinal regression is widely used in scenarios where labels are discrete yet inherently ordered.
arXiv AI
Jul 28
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation
arXiv:2607. 23838v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) lets a large language model answer questions using documents retrieved from an external knowledge base at query time.
arXiv AI
Jul 28
MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents
arXiv:2607. 23870v1 Announce Type: cross Abstract: Smart-city airspace is transforming Uncrewed Aerial Vehicles (UAVs) from passive sensing platforms into cyber-physical decision makers that must follow operational rules under degraded observations and ambiguous language.
arXiv AI
Jul 28
Understanding Machine Unlearning Through the Lens of Mode Connectivity
arXiv:2607. 23970v1 Announce Type: cross Abstract: Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch.
arXiv AI
Jul 28
Disentangling Semantic Attention from Structural Bias in the Attention Manifold
arXiv:2607. 24017v1 Announce Type: cross Abstract: The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws.
arXiv AI
Jul 28
Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty
arXiv:2508. 08992v4 Announce Type: replace Abstract: Real-world decision-making often involves uncertainty expressed in linguistic rather than numerical terms, and Prospect Theory (PT) provides a classic framework for modeling human behavior under such uncertainty.
arXiv AI
Jul 28
PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment
arXiv:2508. 05132v3 Announce Type: replace-cross Abstract: As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical.
arXiv AI
Jul 28
From "Help" to Helpful: A Hierarchical Assessment of LLMs in Mental e-Health Applications
arXiv:2602. 18443v2 Announce Type: replace-cross Abstract: Psychosocial online counselling frequently encounters generic subject lines that impede efficient case prioritisation.
arXiv AI
Jul 28
Exact and Asymptotically Complete Robust Verifications of Neural Networks via Ising Solvers
arXiv:2603. 00408v2 Announce Type: replace-cross Abstract: We present an Ising-compatible framework for formal neural-network robustness verification under bounded input perturbations.
arXiv AI
Jul 28
xMIx: High-Performance Serving-Time Platform for Mechanistic Interpretability Apps
arXiv:2607. 22595v1 Announce Type: new Abstract: Mechanistic interpretability (MI) has emerged as a powerful approach for analyzing and intervening in inference computations, with a growing number of applications such as jailbreak attempt detection, truthfulness evaluation, and hallucination detection.
arXiv AI
Jul 28
StanceBench: A Benchmark for Audio LLM-Based Interpersonal Stance Evaluation from Speech
arXiv:2607. 22658v1 Announce Type: new Abstract: Speech-to-speech dialogue models increasingly depend on prosody and interactional nuance to convey social intent, yet benchmarks for these cues remain limited.
arXiv AI
Jul 28
MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation
arXiv:2607. 22706v1 Announce Type: new Abstract: This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in generative AI: inefficient retrieval and the absence of source verification.
arXiv AI
Jul 28
Plato-Bio: verification-first biological novelty screening with temporal rediscovery and structural benchmarks
arXiv:2607. 23975v1 Announce Type: new Abstract: Large language model research agents can connect literature retrieval, analysis code, and manuscript preparation, but coherent output does not establish scientific validity.
arXiv Machine Learning
Jul 28
Hidden Boundary Motion in Transformer Optimization: Function-Space Orthogonalization of Affine Weight and Bias Updates
arXiv:2607. 22927v1 Announce Type: new Abstract: Weights and biases are normally optimized as separate parameter tensors, yet they do not represent separate functions when the input to an affine layer has nonzero mean.
arXiv AI
Jul 28
Epistemic Norms for AI Safety and Alignment Research
arXiv:2607. 24243v1 Announce Type: new Abstract: Mainstream AI research emphasises capability growth and tolerates low failure rates when average-case performance is high.
arXiv Machine Learning
Jul 28
Generalization bounds and sample complexity for remaining useful life prediction from complete degradation trajectories
arXiv:2607. 23454v1 Announce Type: new Abstract: Data-driven remaining useful life (RUL) prediction requires complete degradation trajectories for training, yet such run-to-failure data are scarce and expensive.
arXiv Machine Learning
Jul 28
Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling
arXiv:2607. 23518v1 Announce Type: new Abstract: The rapid evolution of generative models has unlocked new potentials in protein binder design, a pivotal task in structural biology, by facilitating end-to-end generation via joint sequence-structure modeling or hallucination.
arXiv AI
Jul 28
Label-free Industrial Fault Detection via Adversarial Inverse Reinforcement Learning: A System for Run-to-Failure Prognostics
arXiv:2607. 22987v1 Announce Type: cross Abstract: Machinery fault detection (MFD) remains heavily reliant on supervised learning, which struggles with the scarcity of fault labels in real-world settings.
arXiv AI
Jul 28
CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation
arXiv:2607. 23647v1 Announce Type: cross Abstract: Large language models (LLMs) can summarize heterogeneous user evidence in natural language, but current LLM recommenders often collapse enduring preferences, transient intent, and exposure-induced behavior into one profile.