arXiv Machine Learning June 3, 2026 By Micha{\l} Brzozowski, Zuzanna Dubanowska, Enrico Cassano, Neo Christopher Chung

Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing

Read the original on arXiv Machine Learning →

arXiv:2605. 25902v2 Announce Type: replace Abstract: Narrowly finetuned language models memorize implanted content verbatim, but auditing what a deployed model has been taught, without access to its weights or training data, remains an open challenge.

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

arXiv AI

Jun 6

FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG

arXiv:2606. 05644v1 Announce Type: new Abstract: When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of retrieval augmentation.

By Zhe Yu, Wenpeng Xing, Tiancheng Zhao, Mohan Li, Changting Lin, Meng Han

llms rag benchmarks safety

arXiv AI

Jul 7

Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)

arXiv:2607. 04223v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does not indicate which sentence is unsupported, or why.

By Mohamed Aly Bouke

rag nlp benchmarks safety

arXiv AI

Jul 23

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations

arXiv:2607. 20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it.

By Hiskias Dingeto

safety

arXiv AI

Jul 22

Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models

arXiv:2607. 19257v1 Announce Type: cross Abstract: Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade.

By Netanel Eliav

llms safety

arXiv AI

Jul 7

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens

arXiv:2607. 03502v1 Announce Type: cross Abstract: Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or counting sequences, producing correct answers with no visible chain-of-thought (CoT).

By Kaley Brauer, Claudio Mayrink Verdun, Samuel Marks

llms robotics

arXiv AI

Jun 15

Verbatim Chunks Beat Extracted Artifacts: A Controlled Ablation of Memory Representations for Long LLM Conversations

arXiv:2601. 00821v3 Announce Type: replace Abstract: A growing class of conversational-memory systems compresses dialogue history into structured artifacts -- extracted facts, decisions, or events -- on the premise that distilled structure retrieves better than raw text.

By Tao An

llms rag efficiency benchmarks

Related stories

FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG

Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP)

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations

Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models

Reading Between the Dots: Decoding Hidden Computation across Filler Tokens

Verbatim Chunks Beat Extracted Artifacts: A Controlled Ablation of Memory Representations for Long LLM Conversations