Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
Evaluating reasoning quality in multi-agent LLM systems is challenging, especially for open-ended tasks without reference answers. We investigate whether intrinsic confidence signals, token-level log-probabilities from decoding, can predict reasoning quality as assessed by LLM-as-judge evaluation.
Writing Individualized Education Programs (IEPs) is a high-labor, knowledge-intensive document burden; English-language research has demonstrated that generative AI can significantly reduce drafting time, yet automated IEP generation in Traditional Chinese remains virtually unexplored due to domain data scarcity, strict privacy regulations, and the absence of local evaluation benchmarks. We propose a low-resource fine-tuning pipeline centered on Corpus-Grounded Feature Diffusion (CGFD): (1) 25 dual-expert high-score seed transcripts are selected via a tau threshold with flag-aware score caps; (2) a FeatureProfile (sentence length, structure, quantification templates) is extracted from seeds and injected into LLM prompts alongside Verbalized-Sampling-style diversity control to drive diffusion; (3) 15 expert gold seeds are used as diffusion anchors, targeting 585 samples; 567 valid diffusion samples are obtained, yielding a 582-sample training set used to fine-tune Breeze-7B with QLoRA; (4) schema-constrained inference via Grammar-Constrained Decoding (GCD) enforces a hierarchical SMART Goal Ladder schema at inference time.
What Fourier analysis misses The post Sequential Fitting: A Different Perspective on the Spectral Bias of Neural Networks appeared first on Towards Data Science .
Formal neural network verification -- proving that a network satisfies safety properties for \emph{all} inputs in a specified domain -- is bounded in practice by GPU memory: standard implementations of bound-propagation algorithms (IBP, CROWN, $α$-CROWN) require weight and relaxation-coefficient matrices to reside entirely on one accelerator. We adapt two parallelism techniques originally developed for large-scale model training to the \texttt{auto\_LiRPA}\,/\,$α,β$-CROWN verification framework.
Two-view correspondence learning aims to distinguish true correspondences (inliers) from false ones (outliers) in image pairs by leveraging their underlying differences. Existing methods mainly rely on coordinate-based geometric consistency.
Multilingual safety evaluation of large language models (LLMs) has predominantly relied on direct translation (DT) of English benchmarks into target languages - an approach that converts surface-level linguistic form while failing to reflect the cultural context embedded in threat scenarios, social norms, and legal frameworks. We construct paired DT and culturally-adapted (CA) datasets via 1:1 seed matching for four languages - Korean (KO), Japanese (JA), Thai (TH), and Khmer (KM) - and compare Attack Success Rate (ASR) and Cultural Realism scores across four open-source LLM.
Egocentric vision offers a first-person view of human perception and decision making, yet its potential for traffic-safety prediction remains underexplored. In this work, we study the decoding of pedestrian crossing intentions from short egocentric video clips.
Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information. However, Multi-modal Large Language Models (MLLMs), which process both text and images, introduce unique privacy challenges that remain underexplored.
Chinese discriminatory-language detection is challenging because harmful intent is often implicit and context-dependent. We propose MAAM (Myopia--Astigmatism Anchor Mechanism), a lightweight, model-agnostic framework inspired by functional visual blur: rather than preserving every token equally, MAAM retains discrimination-relevant semantic anchors and calibrates them with C--I--S contextual priors (Contextual Tone, Group Identity, and Stance Polarity).
Tool-using LLM agents interact with the world through actions that persist state in artifacts (e. g.
arXiv:2606. 07277v1 Announce Type: cross Abstract: Secure aggregation allows a server to aggregate users' local updates while preserving update privacy.
arXiv:2505. 10892v2 Announce Type: replace Abstract: Post-training LLMs with RLHF and preference optimization methods (e.
arXiv:2602. 05833v2 Announce Type: replace Abstract: There is a need for synthetic training and test datasets that replicate statistical distributions of original datasets without compromising their confidentiality.
arXiv:2606. 06531v1 Announce Type: new Abstract: The critical question after a correct driving veto is not only whether a maneuver is unsafe, but whether the blocked interaction admits a lawful, auditable, and responsibility-bounded repair.
arXiv:2606. 06534v1 Announce Type: cross Abstract: Longitudinal medical visual question answering (VQA) requires reasoning about anatomical differences between an image of a current time point and an image of a referred time point.
arXiv:2606. 06877v1 Announce Type: cross Abstract: Task planning often suffers from severe efficiency bottlenecks when robots must reason over long-horizon action sequences under complex logical constraints, including object affordances, spatial relationships, and sequential action dependencies.
arXiv:2606. 07033v1 Announce Type: new Abstract: Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events, including categories unseen during training.
arXiv:2606. 06892v1 Announce Type: new Abstract: Scalable data attribution methods typically assign isolated utility scores to individual training examples.
arXiv:2606. 07515v1 Announce Type: cross Abstract: We investigate the probabilistic reasoning capabilities of large language models through a controlled benchmarking study on discrete probability problems.
arXiv:2606. 07325v1 Announce Type: cross Abstract: We study the minimax rate of estimating a future value $\mu_{t_n+h}$ of a curve $t\mapsto\mu_t$ in the $2$-Wasserstein space $\mathcal{P}_2(\mathbb{R}^d)$ from finitely many noisy snapshots of its past, under an adiabatic bound $\|\nabla_t^k v\|\le\varepsilon$ on the $k$-th covariant derivative of the velocity field.