Squish and Release: Exposing Hidden Hallucinations by Making Them Surface as Safety Signals
Language models detect false premises when asked directly but absorb them under conversational pressure, producing authoritative professional output built on errors they already identified. This failure - order-gap hallucination - is invisible to output inspection because the error migrates into the activation space of the safety circuit, suppressed but not erased. We introduce Squish and Release (S&R), an activation-patching architecture with two components: a fixed detector body (layers 24-31, the localized safety evaluation circuit) and a swappable detector core (an activation vector controlling perception direction). A safety core shifts the model from compliance toward detection; an absorb core reverses it. We evaluate on OLMo-2 7B using the Order-Gap Benchmark - 500 chains across 500 domains, all manually graded. Key findings: cascade collapse is near-total (99.8% compliance at O5); the detector body is binary and localized (layers 24-31 shift 93.6%, layers 0-23 contribute zero, p<10^-189); a synthetically engineered core releases 76.6% of collapsed chains; detection is the more stable attractor (83% restore vs 58% suppress); and epistemic specificity is confirmed (false-premise core releases 45.4%, true-premise core releases 0.0%). The contribution is the framework - body/core architecture, benchmark, and core engineering methodology - which is model-agnostic by design.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis
While deep neural networks have been shown in recent years to outperform other machine learning methods in a wide range of applications, one of the biggest challenges with enabling deep neural networks for widespread dep…
Large Means Left: Political Bias in Large Language Models Increases with Their Number of Parameters
With the increasing prevalence of artificial intelligence, careful evaluation of inherent biases needs to be conducted to form the basis for alleviating the effects these predispositions can have on users. Large language…
MisinformationModels AlignmentHal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models
Large Vision Language Models exhibit remarkable capabilities but struggle with hallucinations inconsistencies between images and their descriptions. Previous hallucination evaluation studies on LVLMs have identified hall…
HallucinationHallucination EvaluationExposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors
Multimodal large language models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet they remain highly susceptible to hallucinations, producing content that is fluent but inconsistent with…
Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator
The diagonal of a model's Fisher Information Matrix (the "Fisher diagonal") has frequently been used as a way to measure parameter sensitivity. Typically, the Fisher diagonal is estimated via squared sampled gradients of…