Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 02009v2 Announce Type: replace Abstract: Retrieval-augmented search agents answer multi-hop questions by repeatedly issuing search queries and accumulating evidence.
arXiv:2511. 19264v2 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) construct molecules through sequential decisions, but their internal policies remain opaque, limiting adoption in drug discovery, where chemists need interpretable rationales for proposed structures.
arXiv:2608. 04451v1 Announce Type: cross Abstract: We give a negative solution to MAIS-O60.
arXiv:2608. 04667v1 Announce Type: cross Abstract: Selective inference (SI) provides statistically valid $p$-values for hypotheses selected by applying an algorithm to the data, correcting for the bias that arises when the same data are used both to select and to test a hypothesis.
arXiv:2608. 05127v1 Announce Type: cross Abstract: Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging.
arXiv:2508. 16440v2 Announce Type: replace-cross Abstract: Urban Air Mobility (UAM) envisions the widespread use of small aerial vehicles to transform transportation in dense urban environments.
arXiv:2608. 04215v1 Announce Type: cross Abstract: The growing diversity of code clone types, from syntactic copies to cross-language semantic clones to AI-generated duplicates, has created a fragmentation crisis in clone detection.
arXiv:2608. 04274v1 Announce Type: cross Abstract: Social media recommendation feeds often optimize for users' immediate impulses rather than preferences they would hold after deeper reflection.
arXiv:2608. 05086v1 Announce Type: new Abstract: Language models differ in how safely they behave and these differences are measured by safety benchmarks.
arXiv:2608. 04071v1 Announce Type: new Abstract: Automatically generating professional multimodal reports comprising both textual analysis and visual charts from structured tabular data is a critical challenge in data intelligence.
arXiv:2608. 04240v1 Announce Type: cross Abstract: Superhuman game engines in domains like chess have made expert-level evaluations easily accessible, yet they communicate what is true without the natural-language explanations that make such expertise educationally useful to experts and non-experts alike.
arXiv:2602. 07453v2 Announce Type: replace Abstract: Decision tree ensembles are widely used in critical domains, making robustness and sensitivity analysis essential to their trustworthiness.
arXiv:2510. 25687v4 Announce Type: replace-cross Abstract: Model inversion attacks pose an open challenge to privacy-sensitive applications that use machine learning (ML) models.
arXiv:2608. 04625v1 Announce Type: new Abstract: Industrial recommendation strategy iteration heavily relies on large-scale A/B experimentation.
arXiv:2608. 04586v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).
arXiv:2510. 02422v4 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks typically optimize a fixed-length adversarial suffix toward a predefined target response with a static optimization strategy.
arXiv:2510. 14190v3 Announce Type: replace Abstract: Diffusion models excel at generation, but their latent spaces are high dimensional and not explicitly organized for interpretation or control.
arXiv:2511. 11413v2 Announce Type: replace Abstract: Consider the problem of finding the best matching in a weighted graph where we only have access to predictions of the actual stochastic weights, based on an underlying context.
arXiv:2608. 04509v1 Announce Type: new Abstract: Vision-language systems combine images with retrieved text, but these sources can disagree or jointly fail to support an answer.
arXiv:2510. 20690v3 Announce Type: replace-cross Abstract: Language models continue to hallucinate despite increases in parameters, compute, and data.