Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 00819v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across diverse natural language tasks, yet their outputs often suffer from hallucinations -- content that is misaligned with factual information.
arXiv:2606. 01504v1 Announce Type: cross Abstract: Semantic retrieval in e-commerce must handle short, noisy, and colloquial queries over large product catalogs with fine-grained attribute distinctions.
arXiv:2606. 01883v1 Announce Type: new Abstract: Open-set recognition (OSR) requires a classifier to reject inputs from unseen classes which is essential in safety-critical settings such as medical imaging.
arXiv:2606. 00320v1 Announce Type: new Abstract: We present an online, distribution-free framework for controlling the Conditional Value-at-Risk (CVaR), extending conformal tail risk control to non-stationary and adversarial environments.
arXiv:2506. 02075v3 Announce Type: replace-cross Abstract: The current state of evaluation in survival analysis is plagued by the persistent use of evaluation metrics in ways that are misaligned with the stated modeling objective.
arXiv:2510. 09330v3 Announce Type: replace Abstract: Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment.
arXiv:2605. 24005v2 Announce Type: replace Abstract: The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data.
arXiv:2606. 01490v1 Announce Type: cross Abstract: We present a controlled experiment evaluating 12 multi-agent LLM collaboration topologies for software architecture design.
arXiv:2606. 00871v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used to generate structured descriptions of street-level imagery for tasks such as streetscape auditing, mapping, and public consultation.
arXiv:2606. 01215v1 Announce Type: cross Abstract: Current 3D spatial reasoning methods face a fundamental trade-off: neuro-symbolic 3D (NS3D) concept learners achieve interpretable reasoning through compositional programs but are constrained to closed-set concept vocabularies and simple programs; end-to-end 3D multi-modal LLMs (3D MLLMs) could handle complex natural language and open-vocabulary concepts but suffer from black-box reasoning without explicit spatial verification.
arXiv:2605. 30169v2 Announce Type: replace-cross Abstract: As autonomous language model agents proliferate, forming an emerging agentic web with real-world consequences, what credibility signals can you use to decide whether to trust an unfamiliar agent in the wild and delegate to it?
arXiv:2605. 27835v2 Announce Type: replace Abstract: We introduce CAREF, a parameter-efficient fine-tuning framework that jointly optimizes predictive accuracy and explanation faithfulness via calibration-aware regularization.
arXiv:2605. 31200v2 Announce Type: replace Abstract: Interpretable machine learning requires models that are accurate and structurally faithful to the data.
arXiv:2605. 31483v1 Announce Type: cross Abstract: Despite Bengali being the sixth most spoken language in the world, no prior work has systematically evaluated hallucination in large language models (LLMs) for Bengali.
arXiv:2606. 01584v1 Announce Type: cross Abstract: Conversational tutoring agents have been shown to improve learning engagement and student outcomes, and large language models (LLMs) are increasingly used in these systems to provide scalable, personalized feedback.
arXiv:2603. 18373v4 Announce Type: replace-cross Abstract: When VLMs answer correctly, do they genuinely rely on visual information?
arXiv:2606. 01703v1 Announce Type: cross Abstract: We address the challenge of generating high-fidelity, long-form soundtracks that remain coherent across scene transitions.
arXiv:2603. 12037v2 Announce Type: replace Abstract: Foundation models based on prior-data fitted networks (PFNs) have shown strong empirical performance in causal inference by framing the task as an in-context learning problem.
arXiv:2606. 00647v1 Announce Type: cross Abstract: Detecting psychological defense mechanisms in conversational text remains a challenging clinical NLP problem.
arXiv:2606. 01640v1 Announce Type: new Abstract: Human mobility generation aims to synthesize realistic trip chains for target populations based on individual features.