{"total":29,"rows":[{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43,"area":null},{"id":"2412.09563","title":"Does Representation Matter? Exploring Intermediate Layers in Large Language Models","created":"2024-12-12","cited_by_count":34,"area":null},{"id":"2510.13290","title":"To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25,"area":null},{"id":"2506.14261","title":"RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?","created":"2025-06-17","cited_by_count":24,"area":null},{"id":"2406.20086","title":"Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs","created":"2024-06-28","cited_by_count":18,"area":null},{"id":"2506.00823","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2505.16491","title":"LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing","created":"2025-05-22","cited_by_count":15,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2504.08820","title":"CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2504.08812","title":"Mechanistic Anomaly Detection for \"Quirky\" Language Models","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2407.18712","title":"Cluster-norm for Unsupervised Probing of Knowledge","created":"2024-07-26","cited_by_count":4,"area":null},{"id":"2502.16385","title":"Toward a Flexible Framework for Linear Representation Hypothesis Using Maximum Likelihood Estimation","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2504.16871","title":"Exploring How LLMs Capture and Represent Domain-Specific Knowledge","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2602.05532","title":"Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2605.00226","title":"Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2410.13215","title":"Balancing Label Quantity and Quality for Scalable Elicitation","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2606.12268","title":"The Impossibility of Eliciting Latent Knowledge","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2602.20400","title":"Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.06335","title":"Eliciting associations between clinical variables from LLMs via comparison questions across populations","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.11448","title":"Deep Minds and Shallow Probes","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.03645","title":"The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.09306","title":"Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2609.31401","title":"Decodable In-Context State and Model Output Across Training","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36316","title":"Training LLMs to Verbalize Evaluation Awareness","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.13928","title":"AI Models Can Provably Hide Arbitrary Capabilities","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.18727","title":"On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}