arXiv Machine Learning July 14, 2026 By Peter Hollows

Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls

Read the original on arXiv Machine Learning →

arXiv:2607. 09791v1 Announce Type: new Abstract: The multiplicative repetition penalty shipped across the LLM inference ecosystem (HuggingFace, vLLM, llama.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

6d ago

What Iterated Self-Feeding Probes of Language Models Measure, and a test that separates the construction from the model

arXiv:2608. 10986v1 Announce Type: cross Abstract: A growing class of methods probes a language model by feeding it its own output: self-consistency, iterated refinement, agentic loops.

By Nicol\'as Vera Z\'u\~niga

llms agents

arXiv Machine Learning

Jul 7

ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems

arXiv:2604. 11943v3 Announce Type: replace-cross Abstract: An OS kernel that runs LLM inference internally can read the model's own next-token logit distribution before any text is generated, and act on it as a governance primitive.

By Daeyeon Son

llms agents fine-tuning benchmarks safety

arXiv Machine Learning

Jul 31

Subtract or Replay? Exact Deletion from Language-Model Memory

arXiv:2607. 27539v1 Announce Type: new Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record.

By Vishwajith Ramesh

fine-tuning

arXiv AI

Aug 11

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

arXiv:2608. 08029v1 Announce Type: cross Abstract: Khatri et al.

By Alizishaan Khatri, Dun Li Chan

llms benchmarks safety

arXiv Machine Learning

Jul 31

Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents

arXiv:2607. 27275v1 Announce Type: new Abstract: Post-training quantization to 4-bit weights is widely reported to be nearly lossless.

By Jiwon Jang, Kisu Yang, Heuiseok Lim, Hyunwoo Park

llms agents efficiency benchmarks safety

arXiv Machine Learning

Jul 1

Signed-Permutation Coordinate Transport for RMSNorm Transformers

arXiv:2606. 31963v1 Announce Type: new Abstract: Modern LLM workflows move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top-$k$ neuron sets, attribution lists, and merge alignments.

By John Sweeney

llms fine-tuning safety

Related stories

What Iterated Self-Feeding Probes of Language Models Measure, and a test that separates the construction from the model

ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems

Subtract or Replay? Exact Deletion from Language-Model Memory

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents

Signed-Permutation Coordinate Transport for RMSNorm Transformers