REVIEW 12 cited by
Representation Engineering for Large-Language Models: Survey and Research Challenges
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Representation Engineering for Large-Language Models: Survey and Research Challenges
read the original abstract
Large-language models are capable of completing a variety of tasks, but remain unpredictable and intractable. Representation engineering seeks to resolve this problem through a new approach utilizing samples of contrasting inputs to detect and edit high-level representations of concepts such as honesty, harmfulness or power-seeking. We formalize the goals and methods of representation engineering to present a cohesive picture of work in this emerging discipline. We compare it with alternative approaches, such as mechanistic interpretability, prompt-engineering and fine-tuning. We outline risks such as performance decrease, compute time increases and steerability issues. We present a clear agenda for future research to build predictable, dynamic, safe and personalizable LLMs.
Forward citations
Cited by 12 Pith papers
-
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
GCAD reduces coherence drift from -18.6 to -1.9 and raises turn-10 trait expression from 78.0 to 93.1 in persona-steering tasks by using gated attention-delta interventions from system prompts.
-
Why MLLMs Struggle to Determine Object Orientations
Orientation information is recoverable from MLLM visual encoder embeddings via linear regression, contradicting the hypothesis that failures originate in the encoders.
-
Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial
A 2x2 factorial experiment on Qwen3.5-4B shows that relational structure and first-person register interact to drive behavioral persistence after functional collapse, while attention tracks lexical surprise and emotio...
-
PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts
Benchmark construction artifacts in hallucination detection corpora allow naive text-similarity baselines to achieve near-perfect scores, and controlled evaluations show most methods perform near chance except SAPLMA ...
-
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
GCAD steering extracts prompt-based attention deltas and gates them at token level, cutting coherence drift from -18.6 to -1.9 while raising trait expression at turn 10 from 78 to 93 on multi-turn persona benchmarks.
-
The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models
LLMs organize prompted social roles along a dominant, stable, and causally steerable granularity axis in representation space that runs from micro to macro levels.
-
Contextual Linear Activation Steering of Language Models
CLAS dynamically adapts linear activation steering strengths to context, outperforming fixed-strength steering and matching or exceeding ReFT and LoRA on eleven benchmarks across four model families with limited labeled data.
-
MidSteer: Optimal Affine Framework for Steering Generative Models
MidSteer is a general affine framework for concept steering in generative models that relaxes optimality assumptions of prior LEACE-based methods to enable directed minimal-disturbance transformations.
-
Composer Vector: Style-steering Symbolic Music Generation in a Latent Space
Composer Vector steers symbolic music generation models in latent space at inference time to control and blend composer styles without retraining.
-
A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models
SLM modules provide a clean low-dimensional emotion subspace with strong speaker-emotion disentanglement while CFM modules show entanglement and poor generalization for activation steering in hybrid TTS.
-
Temporal Preference Concepts and their Functions in a Large Language Model
Causal localization via attribution and patching identifies a temporal preference subgraph in mid-to-upper layers of Qwen3-4B-Instruct-2507, with time-horizon geometry in the residual stream and initial evidence for s...
-
Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning
A scoping review surveying circuit analysis, sparse autoencoders, activation steering, and neurosymbolic frameworks for interpreting and controlling Transformer-based neural networks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.