We study how training data contributes to the emergence of toxic behaviors in large language models. Most prior work on reducing model toxicity adopts reactive approaches, such as fine-tuning pre-trained (and potentially toxic) models to align them with human values. In contrast, we propose a proactive approach, IF-GUIDE, that leverages influence functions to identify and suppress harmful tokens in the training data. To this end, we first show that standard influence functions are ineffective at discovering harmful training records. We then present a novel adaptation that measures token-level attributions from training data to model toxicity, along with techniques for selecting toxic training documents and a learning objective that can be integrated into both pre-training and fine-tuning. Moreover, IF-GUIDE does not rely on human-preference data, which is typically required by existing alignment methods. In our evaluation, we demonstrate that IF-GUIDE substantially reduces both explicit and implicit toxicity-by up to 10$\times$ compared to uncensored models, and up to 3$\times$ compared to baseline alignment methods such as DPO and RAD-across both pre-training and fine-tuning scenarios. IF-GUIDE is computationally efficient: a billion-parameter model is not necessary for computing influence scores; a million-parameter model-with 7.5$\times$ fewer parameters-can effectively serve as a proxy for identifying harmful data. Our code is publicly available at: https://github.com/ztcoalson/IF-Guide

Selective state-space models excel at long-sequence modeling, but their capacity for language representation -- in complex hierarchical reasoning -- remains underexplored. Most large language models rely on \textit{flat} Euclidean embeddings, limiting their ability to capture latent hierarchies. To address this, we propose {\it Hierarchical Mamba (HiM)}, integrating efficient Mamba2 with hyperbolic geometry to learn hierarchy-aware language embeddings for deeper linguistic understanding. Mamba2-processed sequences are projected to the Poincaré ball or Lorentzian manifold with ``learnable'' curvature, optimized with a hyperbolic loss. Our HiM model facilitates the capture of relational distances across varying hierarchical levels, enabling effective long-range reasoning for tasks like mixed-hop prediction and multi-hop inference in hierarchical classification. Experimental results show both HiM variants effectively capture hierarchical relationships across four linguistic and medical datasets, surpassing Euclidean baselines, with HiM-Poincaré providing fine-grained distinctions with higher h-norms, while HiM-Lorentz offers more stable, compact, and hierarchy-preserving embeddings-favoring robustness. The source code is publicly available at https://github.com/BerryByte/HiM.

Deep neural networks are known to develop similar representations for semantically related data, even when they belong to different domains, such as an image and its description, or the same text in different languages. We present a method for quantitatively investigating this phenomenon by measuring the relative information content of the representations of semantically related data and probing how it is encoded into multiple tokens of large language models (LLMs) and vision transformers. Looking first at how LLMs process pairs of translated sentences, we identify inner ``semantic'' layers containing the most language-transferable information. We find moreover that, on these layers, a larger LLM (DeepSeek-V3) extracts significantly more general information than a smaller one (Llama3.1-8B). Semantic information of English text is spread across many tokens and it is characterized by long-distance correlations between tokens and by a causal left-to-right (i.e., past-future) asymmetry. We also identify layers encoding semantic information within visual transformers. We show that caption representations in the semantic layers of LLMs predict visual representations of the corresponding images. We observe significant and model-dependent information asymmetries between image and text representations.

The growing capabilities of large language models (LLMs) in instruction-following and context-understanding lead to the era of agents with numerous applications. Among these, task planning agents have become especially prominent in realistic scenarios involving complex internal pipelines, such as context understanding, tool management, and response generation. However, existing benchmarks predominantly evaluate agent performance based on task completion as a proxy for overall effectiveness. We hypothesize that merely improving task completion is misaligned with maximizing user satisfaction, as users interact with the entire agentic process and not only the end result. To address this gap, we propose AURA, an Agent-User inteRaction Assessment framework that conceptualizes the behavioral stages of interactive task planning agents. AURA offers a comprehensive assessment of agent through a set of atomic LLM evaluation criteria, allowing researchers and practitioners to diagnose specific strengths and weaknesses within the agent's decision-making pipeline. Our analyses show that agents excel in different behavioral stages, with user satisfaction shaped by both outcomes and intermediate behaviors. We also highlight future directions, including systems that leverage multiple agents and the limitations of user simulators in task planning.

Improving energy efficiency in residential buildings is critical to combating climate change and reducing greenhouse gas emissions. Retrofitting existing buildings, which contribute a significant share of energy use, is therefore a key priority, especially in regions with outdated building stock. Artificial Intelligence (AI) and Machine Learning (ML) can automate retrofit decision-making and find retrofit strategies. However, their use faces challenges of data availability, model transparency, and compliance with national and EU AI regulations including the AI act, ethics guidelines and the ALTAI. This paper presents a trustworthy-by-design ML-based decision support framework that recommends energy efficiency strategies for residential buildings using minimal user-accessible inputs. The framework merges Conditional Tabular Generative Adversarial Networks (CTGAN) to augment limited and imbalanced data with a neural network-based multi-label classifier that predicts potential combinations of retrofit actions. To support explanation and trustworthiness, an Explainable AI (XAI) layer using SHapley Additive exPlanations (SHAP) clarifies the rationale behind recommendations and guides feature engineering. Two case studies validate performance and generalization: the first leveraging a well-established, large EPC dataset for England and Wales; the second using a small, imbalanced post-retrofit dataset from Latvia (RETROFIT-LAT). Results show that the framework can handle diverse data conditions and improve performance up to 53% compared to the baseline. Overall, the proposed framework provides a feasible, interpretable, and trustworthy AI system for building retrofit decision support through assured performance, usability, and transparency to aid stakeholders in prioritizing effective energy investments and support regulation-compliant, data-driven innovation in sustainable energy transition.

We propose Point-PNG, a novel self-supervised learning framework that generates conditional pseudo-negatives in the latent space to learn point cloud representations that are both discriminative and transformation-sensitive. Conventional self-supervised learning methods focus on achieving invariance, discarding transformation-specific information. Recent approaches incorporate transformation sensitivity by explicitly modeling relationships between original and transformed inputs. However, they often suffer from an invariant-collapse phenomenon, where the predictor degenerates into identity mappings, resulting in latent representations with limited variation across transformations. To address this, we propose Point-PNG that explicitly penalizes invariant collapse through pseudo-negatives generation, enabling the network to capture richer transformation cues while preserving discriminative representations. To this end, we introduce a parametric network, COnditional Pseudo-Negatives Embedding (COPE), which learns localized displacements induced by transformations within the latent space. A key challenge arises when jointly training COPE with the MAE, as it tends to converge to trivial identity mappings. To overcome this, we design a loss function based on pseudo-negatives conditioned on the transformation, which penalizes such trivial invariant solutions and enforces meaningful representation learning. We validate Point-PNG on shape classification and relative pose estimation tasks, showing competitive performance on ModelNet40 and ScanObjectNN under challenging evaluation protocols, and achieving superior accuracy in relative pose estimation compared to supervised baselines.

Since statistical guarantees for neural networks are usually restricted to global optima of intricate objective functions, it is unclear whether these theories explain the performances of actual outputs of neural network pipelines. The goal of this paper is, therefore, to bring statistical theory closer to practice. We develop statistical guarantees for shallow linear neural networks that coincide up to logarithmic factors with the global optima but apply to stationary points and the points nearby. These results support the common notion that neural networks do not necessarily need to be optimized globally from a mathematical perspective. We then extend our statistical guarantees to shallow ReLU neural networks, assuming the first layer weight matrices are nearly identical for the stationary network and the target. More generally, despite being limited to shallow neural networks for now, our theories make an important step forward in describing the practical properties of neural networks in mathematical terms.

OpenAI's head of ChatGPT says posts appearing to show in-app ads are'not real or not ads' However, OpenAI exec Nick Turley said that the company will take a thoughtful approach if they pursue ads. Those might not exactly be ads you're seeing on ChatGPT, at least according to OpenAI. Nick Turley, OpenAI's head of ChatGPT, clarified the confusion around potential ads appearing with the AI chatbot. In a post on X, Turley said there are no live tests for ads and that any screenshots you've seen are either not real or not ads. The OpenAI exec's explanation comes after another post from former xAI employee Benjamin De Kraker on X that has gained traction, which featured a screenshot showing an option to shop at Target within a ChatGPT conversation.

Players walk clockwise in a circle. When the music stops, everyone sits in a chair. Big Tech is setting in motion its plans for the next gen of lead designers, engineers, AI chiefs, and even CEOs. In Cupertino, Apple execs with familiar faces are retiring or reducing responsibilities. Well, chief operating officer Jeff Williams retired in November, and the speculation is that CEO Tim Cook could follow in the near term. Lisa Jackson, who has led Apple's sustainability efforts since 2013, is now set to retire in January too.

When you purchase through links in our articles, we may earn a small commission. Get a lifetime license to Pansophy's fully private, on-device AI assistant for $79 and run ChatGPT-style tools locally with zero subscriptions, zero data sharing, and zero usage limits (MSRP $199). AI tools are getting more powerful, but also more expensive, more restricted, and more invasive. That's why this new desktop AI tool is turning so many heads: it gives you ChatGPT-style intelligence with none of the trade-offs. Pansophy is a fully local AI desktop assistant that runs entirely on your PC, Mac, Chromebook, or Linux device.