arXiv AI
Jun 8
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
arXiv:2604. 02029v2 Announce Type: replace Abstract: Latent space is rapidly emerging as a native substrate for language-based models.
Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
arXiv:2607. 00083v1 Announce Type: cross Abstract: Language models have changed from unreliable text generators to highly-capable large models with trillions of parameters.
Related stories
arXiv AI
Jul 24
Expectation Alignment of Language Models for Real-World User Expectations
arXiv:2607. 20485v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations.
arXiv Computation and Language
Sep 23
Calibration as a First-Class Criterion in LLM Evaluation
The paper argues that calibration—how well a language model’s confidence aligns with its actual correctness—should be a standard evaluation metric for large language models (LLMs). It notes that while calibration metrics exist, they are rarely applied outside specialized NLP subfields, leading to unverified confidence scores in new models, datasets, and benchmarks. The authors highlight the risks of miscalibration both at deployment (overconfident errors causing harm) and in research workflows (affecting LLM-as-a-judge, synthetic data generation, and active learning). They call for every NLP subfield to pair its primary performance metric with a calibration score, treating calibration as an essential property of every model.
arXiv AI
Jun 9
When Behavioral Safety Evaluation Fails: A Representation-Level Perspective
arXiv:2606. 08044v1 Announce Type: cross Abstract: Large Language Model (LLM) safety has often been evaluated at the behavior level, which provides limited evidence of internal robustness, as these evaluations target outputs rather than representation-level vulnerability under intervention.
arXiv Machine Learning
Jun 4
A Latent Variable Framework for Scaling Laws in Large Language Models
arXiv:2512. 06553v2 Announce Type: replace-cross Abstract: We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs).
arXiv AI
Sep 1
Toward Latent Language Model Skills Steering and Optimization: An Empirical Study
arXiv:2608.29459v1 Announce Type: new Abstract: Skills, as a useful abstraction for the procedural capabilities of large language models (LLMs), capture how models perform structured, multi-step reas...
arXiv AI
Aug 25
Measuring Activation Control in Large Language Models
arXiv:2608.21664v1 Announce Type: new Abstract: Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especiall...
arXiv AI
Jun 2
TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models
arXiv:2606. 00023v1 Announce Type: cross Abstract: The rapid development of Language Diffusion Models (LDMs) challenges the dominant position of auto-regressive competitors in language processing.
arXiv Machine Learning
Jul 1
White-Box Sensitivity Auditing with Steering Vectors
arXiv:2601. 16398v3 Announce Type: replace-cross Abstract: Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators.
arXiv Computation and Language
Sep 24
LiSeCo: Linear Semantic Control for Language Generation
LiSeCo is a lightweight, gradient‑free method that controls language generation by directly intervening on the hidden activations of a token in embedding space. It uses control‑theoretic techniques to steer the generation trajectory away from undesired semantic regions and into a predefined allowed region, ensuring fine‑grained attribute control. The approach is computationally efficient, minimally impacts generation time, and is shown to be effective on tasks such as toxicity, sentiment, and bilingual language steering while preserving text quality.
arXiv AI
Jun 2
Latent Collaboration in Multi-Agent Systems
arXiv:2511. 20639v3 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence.
arXiv AI
Aug 11
Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
arXiv:2510. 21891v2 Announce Type: replace-cross Abstract: To deploy large language models (LLMs) in high-stakes application domains that require substantively accurate responses to open-ended prompts, we need reliable, computationally inexpensive methods that assess the trustworthiness of long-form responses generated by LLMs.