arXiv:2608.18106v1 Announce Type: cross Abstract: Large language models tend to overconfidence, giving assertive answers when the evidence suggests…
Abliteration Mitigation via Refusal Aliases
arXiv:2608.18093v1 Announce Type: cross Abstract: Abliteration, the removal of refusal capabilities from large language models by projecting weight…
Self- and Other-Labels Induce Bidirectional Bias in LLM Judges
arXiv:2608.18091v1 Announce Type: cross Abstract: As LLM-as-a-judge systems become increasingly widespread, self-preference in LLMs — the tendency to…
NE-BERT: A Multilingual Language Model for Nine Northeast Indian Languages
arXiv:2608.18094v1 Announce Type: cross Abstract: Large pretrained language models have demonstrated remarkable capabilities across diverse languages, yet…
Backdoor Learning in Language Models and Vision-Language Models
arXiv:2608.18095v1 Announce Type: cross Abstract: Recent advances in deep learning have significantly enhanced the capabilities of Natural Language…
Why Your Model Only Learns What the Labels Teach It
A supervised model does not learn the world; it learns the labels a team of annotators assigned to pixels. If those labels disagree with each other, blur…
Fractional Decay KV-Cache: Ownership-Aware Memory Management for Improved Inference Relevancy in Dialog Systems
arXiv:2608.18098v1 Announce Type: cross Abstract: Key-value (KV) caching is essential for efficient autoregressive inference in transformer based dialog…
AI News Brief Hourly Summary 2026-08-20 13h : 15 posts
15 posts published in the last hour 10:33Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities 10:33Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems 10:33Latent Space Refusal Anchoring for Low-Resource African…
Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities
arXiv:2608.18090v1 Announce Type: cross Abstract: Inside a modern language model sits a single internal direction that tracks how positive or negative a…
Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems
arXiv:2608.19140v1 Announce Type: new Abstract: Frontier language models are compared, marketed, and benchmarked on capability — what their best or…
Latent Space Refusal Anchoring for Low-Resource African Languages: Mechanistic Safety Recovery Without Retraining
arXiv:2608.18089v1 Announce Type: cross Abstract: Instruction-tuned models often refuse harmful requests in English but comply with the same requests in…
Unlocking hidden revenue streams with market models
Each day, an airline transports tens of thousands of passengers on hundreds of flights. Often these are not straightforward point-to-point routes, with…
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication
arXiv:2608.19161v1 Announce Type: new Abstract: Language-model agents can communicate through continuous hidden states that are invisible in public…
Anthropic’s most capable model, codenamed “Model 2,” is for internal use only
Anthropic uses an unpublished AI model internally that is more powerful than any publicly available version of Claude. The article Anthropic’s most…
SuTRA : Structurally-Unified Tokenization with Root Awareness
arXiv:2608.18087v1 Announce Type: cross Abstract: Existing subword tokenizers optimize statistical compression but ignore morphological structure,…
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
arXiv:2608.19073v1 Announce Type: new Abstract: An agent still learning its environment should be cautious while ignorant and bold once confident. The…
Tuning the Stochastic Machine: A Systems Engineer’s Operating Model for Human-AI Engineering
arXiv:2608.19125v1 Announce Type: new Abstract: When an expert corrects an LLM assistant’s error, the correction usually dies with the session, and the…
Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering
arXiv:2608.19029v1 Announce Type: new Abstract: Accurate and responsible medical question answering (QA) is important in healthcare, where complex cases…