Home Knowledge Base Hidden Representation Steering

Hidden Representation Steering

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders

arXiv:2606.07473v1 Announce Type: new Abstract: Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconnected from the input. We investigate whether hallucinations can be detected and mitigated through Whisper's internal representations. We extract audio encoder activations and evaluate two representation spaces: raw Whisper activations and Sparse AutoEncoder (SAE) latents.

arXiv CS 2d ago

SV-Detect: AI-generated Text Detection with Steering Vectors

new Abstract: Detecting machine-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks. We propose a fake-text detector based on steering vectors extracted from the hidden representations of a frozen language model. At each layer, we construct a direction that separates human-written from machine-generated text, and represent each input by its layer-wise alignment with these directions.

arXiv CS 2d ago

ATLAS: Verifier-Guided Adaptive Latent Activation Steering for Efficient LLM Reasoning

arXiv:2601.03093v2 Announce Type: replace Abstract: Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without updating model parameters. However, most existing approaches rely on fixed steering policies and static intervention strengths, which limit their robustness across problem instances and often result in over- or under-steering. We propose...

arXiv CS 1d ago

CASteer: Cross-Attention Steering for Controllable Concept Erasure

arXiv:2503.09630v5 Announce Type: replace Abstract: Diffusion models have transformed image generation, yet controlling their outputs to reliably erase undesired concepts remains challenging. Existing approaches usually require task-specific training and struggle to generalize across both concrete (e.g., objects) and abstract (e.g., styles) concepts. We propose CASteer (Cross-Attention Steering), a training-free framework for concept erasure in diffusion models using steering vectors to...

arXiv CS 2d ago

Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech

arXiv:2606.01479v1 Announce Type: new Abstract: Integrating large language models (LLMs) into text-to-speech (TTS) systems has improved speech expressiveness, yet interpretable emotional control remains challenging. Existing approaches primarily rely on external conditioning or global activation steering, offering limited insight into the internal representations underlying emotional control.

arXiv CS 8d ago

Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization

arXiv:2606.01252v1 Announce Type: new Abstract: Multi-target cross-lingual text summarization (MTXLS), which summarizes a source document into multiple target languages, is increasingly important as users consume content in diverse languages, but remains underexplored. To address this gap, we introduce multi-target cross-lingual element-aware (MEA), a new MTXLS benchmark covering 24 target languages. We benchmark end-to-end and pipeline approaches across various LLMs and show that MTXLS...

arXiv CS 8d ago

Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States

Announce Type: replace Abstract: Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning types. We test this by probing Qwen3-14B on three benchmarks spanning the classical trichotomy: LogiQA 2.0 (deductive), ARC-Challenge (inductive), and $\alpha$NLI (abductive). At layer 32 of 40, linear probes achieve 100\% cross-validated accuracy with well-separated geometry (intrinsic dimensionalities: 20.6,...

arXiv CS 5d ago

Linear Probes Detect Task Format, Not Reasoning Mode in Language Model Hidden States

arXiv:2606.02907v1 Announce Type: new Abstract: Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning types. We test this by probing Qwen3-14B on three benchmarks spanning the classical trichotomy: LogiQA 2.0 (deductive), ARC-Challenge (inductive), and $\alpha$NLI (abductive). At layer 32 of 40, linear probes achieve 100\% cross-validated accuracy with well-separated geometry (intrinsic...

arXiv CS 7d ago

Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models

Announce Type: replace Abstract: Vision-Language-Action (VLA) models have emerged as a promising approach for general-purpose robot manipulation. However, little research has mechanistically explored when and why they generalize across objects, scenes, and instructions. To probe internal representations, we train Sparse Autoencoders (SAEs) on the VLA's hidden-layer activations.

arXiv CS 1d ago

Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search

arXiv:2512.08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age. To mitigate these biases, existing approaches frequently depend on curated prompt datasets - either manually constructed or generated with large language models (LLMs) - as part of their training and/or evaluation procedures. Beside the curation...

arXiv CS 1d ago