Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation

arXiv:2609.34033 · cs.CL · Submitted 2026-09-27 · Read on arXiv

cs.CL

Submitted: 2026-09-27

Updated: 2026-09-27

Terminology

• Ablation — 9× in this paper · explained in 1 episode
• Fidelity — 7× in this paper · explained in 2 episodes
• Activation Oracle — 6× in this paper
• Direct Preference Optimization — 6× in this paper
• Embeddings — 6× in this paper · explained in 2 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Interpretability — 4× in this paper · explained in 15 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Two-Stage Framework — 3× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Decode — 2× in this paper · explained in 2 episodes
• Direct Preference Optimization (DPO) — 2× in this paper · explained in 9 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 4 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Activation Patching — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Commentary — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cross-Model Transfer — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Objective Mismatch — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent
• Building Better Activation Oracles
• Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations
• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
• Rep2Text: Decoding Full Text from a Single LLM Token Representation
• Universal and Transferable Adversarial Attacks on Aligned Language Models

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