Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation

arXiv:2608.30902 · cs.CL · Submitted 2026-08-31 · Read on arXiv

cs.CL

Submitted: 2026-08-31

Updated: 2026-08-31

Code: https://github.com/alessioGalatolo/activ-pref-probe

Terminology

• Accuracy — 36× in this paper · explained in 1 episode
• Linear probe — 21× in this paper · explained in 2 episodes
• Alignment — 17× in this paper · explained in 1 episode
• Adaptation — 11× in this paper · explained in 1 episode
• LLM-as-a-Judge — 7× in this paper · explained in 3 episodes
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Clustering — 4× in this paper · explained in 2 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• Actor — 2× in this paper · explained in 3 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Low-Resource Languages — 2× in this paper · explained in 4 episodes
• Abstention — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Convergence Guarantees — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Linear Probing — 1× in this paper · explained in 2 episodes
• Pseudo-labels — 1× in this paper · explained in 2 episodes
• SFT and Preference Optimisation — 1× in this paper
• Supervised Fine-Tuned — 1× in this paper
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• A General Language Assistant as a Laboratory for Alignment
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Constitutional AI: Harmlessness from AI Feedback
• No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
• UltraFeedback: Boosting Language Models with Scaled AI Feedback
• Toy Models of Superposition
• Gemma 3 Technical Report
• The Llama 3 Herd of Models
• Qwen2.5 Technical Report
• Qwen3 Technical Report
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering