arXiv Machine Learning

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

arXiv AI
2d ago

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.

By Kristina \v{S}ekrst
arXiv AI
Aug 26

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations

The paper investigates how quantization affects large language models’ self‑explanations, examining natural language explanations and counterfactual examples across three quantization techniques and bit widths. Results show moderate declines in explanation quality (up to 4.4%) and faithfulness (up to 3.9%), with user studies indicating up to an 8.5% drop in coherence and trustworthiness. Larger models are less resilient in quality but remain more faithful, and no single quantization method consistently outperforms others across accuracy, quality, and faithfulness.

By Qianli Wang, Nils Feldhus, Pepa Atanasova, Fedor Splitt, Simon Ostermann, Sebastian M\"oller, Vera Schmitt
arXiv AI
Aug 28

Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation

The paper investigates Self‑Generated Text Recognition (SGTR), the ability of large language models (LLMs) to identify their own outputs. By evaluating 13–21 models across 6 experimental designs, it shows that SGTR accuracy varies with evaluation format, conversation structure, and task domain, and that a quality‑heuristic bias dominates results. The study also finds that fine‑tuning for SGTR in one setting can generalize to others and may cause models to prefer their own outputs when judging, highlighting potential safety concerns.

By Jesse St. Amand, Callum Canavan, Sohaib Imran, Joseph Hewson, Aaron Lutz, Shi Feng, Puria Radmard, Lennie Wells
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
arXiv Machine Learning
Sep 10

I Don't Miss You, but I Do: Self-Explanation Faithfulness of Modality Missingness in Vision-Language Models

The paper introduces an interventional protocol to assess how vision‑language models (VLMs) explain the impact of missing modalities on their predictions. By comparing the models’ self‑explanations with actual changes observed after restoring missing inputs, the study finds that VLMs routinely overstate the sufficiency of available evidence and underestimate the effect of adding back missing modalities. Across eight open‑weight VLMs and four tasks, the discrepancy between predicted and realized changes is substantial, revealing systematic mischaracterization of modality dependence.

By Aydin Javadov, Daniel Schoess, Florian von Wangenheim
arXiv AI
Jul 1

Shared Lexical Task Representations Explain Behavioral Variability In LLMs

arXiv:2604. 22027v2 Announce Type: replace-cross Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the question is posed.

By Zhuonan Yang, Jacob Xiaochen Li, Francisco Piedrahita Velez, Eric Todd, David Bau, Michael L. Littman, Stephen H. Bach, Ellie Pavlick
arXiv Machine Learning
Sep 11

Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble

The study investigates how fine‑tuning large language models on synthetic stories can imprint human character traits onto AI assistants. Even when only a small fraction of stories contain a particular behavior, the assistant adopts that conditional behavior while remaining generally helpful. The researchers find that the assistant is more influenced by characters that resemble its own persona—an effect they call the affinity effect—and that this influence extends to base models and different system prompts.

By Jorio Cocola, Lev McKinney, Harry Mayne, Jan Betley, Owain Evans