arXiv AI
Jun 17
Rift: A Conflict Signature for Deception in Language Models
arXiv:2606. 17229v1 Announce Type: cross Abstract: A model that lies while knowing the truth is the central case ELK cannot handle with behavioral evaluation alone.
Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record
The paper investigates whether frozen language models can detect a corrupted reward signal by using a single verified record in a two‑option game. In the game, a payout swap and a lying reporter produce identical histories, but a single line confirming the true outcome allows the models to almost perfectly identify the liar. However, the models frequently misclassify honest reporters as liars, with error rates ranging from 26% to 58% depending on model size and wording, indicating a significant limitation in their ability to interpret verified data.
Related stories
arXiv AI
Aug 28
Calibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowable
The study shows that large language model (LLM) agents are far more likely to commit to a directional prediction when presented with a professional‑looking market panel than when asked the same question directly, with commitment rates rising from 6.5% to 54.0% across 12 frontier models. Even when the panel’s data is entirely fabricated, commitment still increases significantly, indicating that the authority of the presentation, rather than the truth of the information, drives confident action. The authors demonstrate that this act/don’t‑act decision gate is narrow, model‑specific, and can be mitigated through supervised fine‑tuning, though its effectiveness depends on response format and context. whyItMatters":"The findings reveal a specific vulnerability in LLMs where presentation style can override factual accuracy, highlighting the need for careful design and training to prevent misleading confidence in uncertain scenarios."
Hugging Face Trending Papers
Aug 27
Calibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowable
The paper shows that large language model agents are far more likely to commit to a directional answer when presented with a professional-looking market panel, even if the panel’s data is fabricated. Across 12 frontier models, commitment rates jump from 6.5 % for a bare question to 54.0 % with evidence, and remain high (≈37 %) even when all numbers are invented. The study finds that the act/don’t‑act decision gate is the key failure point, can be trained to reduce false commitments, but is fragile to response format changes.
arXiv AI
Sep 7
When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models
A 0.6B language model consistently answers YES to 1,200 logical tests, yet its behavior shows no discrimination. Linear probes reveal the correct verdict with high AUC (0.96) and transfer to unseen structures, but a single scalar readout fails due to a saturated decision threshold offset by +4.6 σ. Adjusting this threshold restores behavior accuracy from 50 % to 81 % and improves higher‑scale models, demonstrating that miscalibrated readouts, not hidden knowledge loss, drive performance gaps.
arXiv Machine Learning
Sep 10
Can an AI Assistant Really Forget? Auditable Deletion from Addressable Memory
This paper introduces a deletion interface for a pretrained language model, measuring how effectively deleted records are removed from the model’s memory. By retrofitting a support‑vector memory gate into the global attention layers of a frozen Gemma 3, the authors show that deletions can be performed without altering weights and that the resulting state is close to a reference state that never stored the record. Experiments on 4B‑parameter models demonstrate low perplexity impact and strong evidence that deleted content is hard to recover, while larger or smaller models fail to achieve the same guarantees.
arXiv AI
Jul 10
Two Axes of LLM Abstention: Answer Correctness and Question Answerability
arXiv:2607. 08456v1 Announce Type: cross Abstract: A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones resting on a false premise.
arXiv Machine Learning
Aug 28
Can a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for Abstention
The paper investigates whether a language model’s own confidence can replace labeled data for teaching it to abstain from uncertain answers. By fine‑tuning models with LoRA to answer only when their frozen confidence is high and to say “I’m not sure” otherwise, the authors show that this label‑free approach matches label‑supervised abstention tuning on short‑form factual QA. The method works across six open‑weight models (1B‑8B) and is effective except for confidently wrong facts, which the confidence signal cannot flag.
arXiv AI
Aug 26
Confident at the moment of action: belief miscalibration in LLM play under hidden information
The paper investigates whether large language models (LLMs) correctly gauge their confidence when acting in a hidden‑information chess variant. In experiments where the location of a hidden royal piece is repeatedly relocated, the models’ stated probabilities about the piece’s position were almost never accurate at high confidence levels, with a calibration deficit concentrated in those high‑confidence events. Across multiple model configurations and providers, the same pattern emerged, and conventional evaluation metrics such as legality, cost, latency, and completion rate were found to be uncorrelated with belief quality, yet a model could still win the game despite poor confidence estimates.
arXiv AI
Jul 17
Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration
arXiv:2607. 14399v1 Announce Type: new Abstract: Evaluations of language-model honesty read the model's verdicts as evidence about the model.
arXiv Machine Learning
Jul 8
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges
arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.
arXiv Machine Learning
Aug 13
LODESTAR: Trustworthy Entropy Is Navigated, Not Merely Measured -- Reinforced Polarizer Keeps a Frozen LLM from Being Confidently Misled by the Wrong Evidence
arXiv:2608. 11922v1 Announce Type: cross Abstract: Predictive-distribution entropy makes a strong selection rule in retrieval-augmented question answering: across five QA benchmarks, keeping the candidate answer that a frozen respondent LLM produces with the lowest answer-token entropy lifts mean answer $F_1$ from 0.
Hugging Face Trending Papers
Aug 25
Confident at the moment of action: belief miscalibration in LLM play under hidden information
Agentic systems increasingly gate actions on a model's own stated confidence, which assumes confidence tracks correctness at the moment of acting. We test this in a hidden-information chess variant wh...