Activation steering controls model behavior by editing internal activations at inference time, and finds that a single MLP neuron is eval-correlated but not causal at both scales, and that scanning the real Pile yields a natural-text baseline competitive with the optimizer for the internal direction.
Abstract
Activation steering controls model behavior by editing internal activations at inference time. We study its input-side dual: optimizing a fluent prompt so that a chosen internal latent is driven toward zero, with no inference-time model access. Our target is an"evaluation-awareness"latent-linearly readable and steerable in recent work-whose control would threaten the validity of safety evaluations if models behave differently when they detect being tested. Adapting Fluent Dreaming / EPO with a negated feature term (GCG-style token optimization plus a self-cross-entropy fluency regularizer, swept over a fluency weight), we suppress the latent under five target constructions-a CAA direction, a subspace norm, an SAE feature, a single MLP neuron, and a behavioral logit-on Llama-3.2-3B and Llama-3.1-8B. The latent is robustly suppressible ($z\approx-7$), and a causally-validated Llama Scope SAE feature can be fully and selectively turned off. But our controls tell a cautionary story about the CAA direction: a placebo random direction is suppressed just as hard and shifts behavior just as far, and when we hold a real eval passage in context and optimize only a prefix, suppressing the eval-direction fails to reduce-and slightly increases-the model's behavioral eval judgment. Activation-readability, in short, is not behavioral controllability. We further find that a single MLP neuron is eval-correlated but not causal at both scales, and that scanning the real Pile yields a natural-text baseline competitive with the optimizer for the internal direction. A positive control validates our erasure detector, bounding an erasure-vs-rotation question earlier left open.
The Activation Controllability Benchmark is introduced to quantify the extent to which models can modulate their residual stream via natural-language instruction, and suggests that control over the activation space itself could become a confound for monitoring as introspective capabilities increase.
Marek Mateusz Kowalski, J. Rivera, Uzay Macar et al.· 0 citations
An integrated conceptual frame-work that couples attention- and perturbation-based explainability with lightweight hallucination-detection signals and token-efficient inference strategies is presented, and a set of cross-cutting consistency metrics are instrumented with a set of cross-cutting consistency metrics.
Sakshi Parate, Shreyans Sanyal· Advanced International Journ...· 0 citations
A novel training-free inference strategy for MLLMs that explicitly decouples perception and reasoning is presented, and a novel metric, the vision-to-text attention ratio, is proposed, to dynamically gauge the model's cognitive focus.
Haoqiang Kang, Liupeng Li, Kuofeng Gao et al.· 0 citations
Hallucination remains a critical challenge in large language models (LLMs), where early factual errors compound through autoregressive generation in a snowballing effect that neither post-hoc correction nor weight-level intervention can effectively preempt. We propose DescaPE (DEcoding Signal Control Against Path Error-snowballing), a decoding framework that leverages internal model signals to suppress hallucination-prone trajectories at inference time. Through sliding-window MLP ablation, we identify a factual-salient layer span within LLMs whose derived signal is selectively elevated for factual tokens and exhibits anomalous spikes at hallucination-prone steps. We train a lightweight probe to approximate this signal from a single forward pass and integrate it into candidate scoring to penalize high-risk continuations while rewarding factually grounded ones. Experiments across five factuality benchmarks on three LLMs demonstrate that DescaPE achieves factuality improvements over decoding-time baselines in multiple settings, while incurring only 1.10x latency overhead in our efficiency evaluation. Our code is available at https://github.com/hayeonggg/DESCAPE.
Hayeong Ryu, Jungmin Yun, B. Lim et al.· 0 citations
Task vectors enable post-training model editing by identifying semantically meaningful directions in weight space, typically computed as the difference between a fine-tuned model and its pretrained initialization. However, this reliance on fine-tuning makes discovering such directions costly and limits the practicality of post-training model editing. To address this limitation, we introduce Training-Free Task Vectors (TFTVs), a novel method to compute task-vector-like directions without requiring fine-tuning. Our method maps activation steering vectors to rank-one weight-space edits using only forward-pass statistics, while satisfying arithmetic properties that directly support learning via addition, forgetting via subtraction, and the composition of multiple edits. Empirically, we evaluate TFTVs on large language model behavioral control tasks and show that they consistently amplify, suppress, and compose target behaviors while preserving general knowledge and problem-solving skills. We also validate our method against other editing and steering baselines, experimentally demonstrating that TFTVs achieve stronger trait control with better or competitive utility preservation. We hope our work opens new directions for the community in post-training model editing and broader training-free model control. Code is available on the project website: tftv-llm.github.io.
G. Perin, Lucas Boscaini, André Araújo et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
