arXiv AI September 25, 2026 By Kristina \v{S}ekrst

Who Put the I in AI? Provenance and the Admissibility of Machine Self-Report

The paper investigates how large language models (LLMs) describe themselves, noting that their self‑reports vary with question phrasing. By tracing the provenance of 66 pretraining checkpoints, post‑training stages, and 90,000 continuations across four corpora, the authors show that denial statements are scarce in raw data but appear densely in curated dialogues, and that supervised fine‑tuning makes first‑person claims default while preference optimization suppresses alternatives. The study concludes that both trained denials and affirmations are equally sensitive to framing and fail to meet epistemic criteria for admissible testimony.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

4d ago

"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It

arXiv:2609.25021v1 Announce Type: new Abstract: Large Language Models (LLMs) tend to add disclaimers like "I'm just an AI" when asked about something related to themselves. The self-reports from such...

By J\k{e}drzej Maczan

llms safety

arXiv Machine Learning

Aug 4

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

arXiv:2507. 02778v3 Announce Type: replace-cross Abstract: Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths.

By Ken Tsui

llms fine-tuning 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

Aug 25

Evaluation Awareness in Language Models: Representation, Verbalization, and Control

arXiv:2608.21766v1 Announce Type: cross Abstract: Both capability and safety benchmarks rest upon the assumption that the behavior of language models undergoing a test is informative about their beha...

By Farzaneh Heidari, Amin Memarian, Guillaume Rabusseau

llms fine-tuning benchmarks safety

arXiv Computation and Language

Sep 11

Probing for Knowledge Attribution in Large Language Models

The paper introduces a method for identifying the dominant knowledge source behind large language model (LLM) outputs, distinguishing between faithfulness violations (misuse of provided context) and factuality violations (errors in internal knowledge). A simple linear probe trained on hidden representations can reliably classify this source, and the authors present AttriWiki, a self‑supervised pipeline that generates labeled training data by prompting models to recall withheld entities or read them from context. Probes trained on AttriWiki achieve high Macro‑F1 scores across several models and datasets, generalize zero‑shot to a benchmark, and show that attribution mismatches can increase error rates by up to 70%. "whyItMatters":"The study demonstrates that knowing the source of an LLM’s answer is crucial for effective mitigation of hallucinations, as attribution mismatches significantly raise error rates."

By Ivo Brink, Alexander Boer, Dennis Ulmer

llms benchmarks safety

arXiv Computation and Language

Sep 2

Can LLMs Reliably Self-Report Adversarial Prefills, and How?

The study investigates whether large language models (LLMs) can reliably detect when their own responses have been manipulated by adversarial prefill attacks. Across ten instruction‑tuned LLMs ranging from 3B to 70B parameters and four safety benchmarks, none consistently recognized compromised outputs, with models claiming intent on prefilled responses at an average of 25.3%. The research identifies that introspective signals mainly arise from safety reasoning and refusal, and that training to improve introspection can paradoxically increase attack success, underscoring the fragility of LLM self‑reporting in safety contexts.

By Quang Minh Nguyen, Uzair Ahmed, Taegyoon Kim