arXiv AI
Evaluating Steering Techniques using Human Similarity Judgments
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 2
Uncovering the Computational Ingredients of Human-Like Representations in LLMs
arXiv:2510.01030v2 Announce Type: replace Abstract: The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust repres...
arXiv AI
2d ago
Steering Geometry: Validating Human Value Geometry in LLM Steering Space
arXiv:2609.06289v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inferenc...
arXiv AI
Jul 22
Probabilistic Concept-Aware Steering for Trustworthy LLM Inference
arXiv:2607. 18259v1 Announce Type: new Abstract: Steering vectors (SVs), an inference-time intervention technique for large language models (LLMs), guide the generation process by adding a concept-specific direction vector to intermediate activations during inference.
arXiv AI
Jul 15
Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing
arXiv:2607. 12195v1 Announce Type: cross Abstract: Semantic memory retrieval can be conceptualized as navigation through conceptual space.
arXiv Machine Learning
Jul 9
Towards Understanding Steering Strength
arXiv:2602. 02712v2 Announce Type: replace Abstract: A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations.
arXiv Computation and Language
Aug 31
Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representations
The paper investigates the intrinsic dimension (ID) of large language model (LLM) representations as an indicator of linguistic complexity. By comparing ID across model layers for coordination vs. subordination, right‑branching vs. center‑embedding, and unambiguous vs. ambiguous attachment, the authors find consistent ID differences that align with established complexity contrasts. Experiments across six LLMs, including representational similarity and layer pruning analyses, confirm that more complex phenomena produce higher ID profiles, with peaks occurring at different layers for each contrast.