Cover Image

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Liu, Ming
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language Machine Learning I.2.7; I.2.6; J.3
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Model selection meets clinical semantics: Optimizing ICD-10-CM prediction via LLM-as-Judge evaluation, redundancy-aware sampling, and section-aware fine-tuning
by: Dai, Hong-Jie, et al.
Published: (2025)

Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs
by: Manczak, Blazej, et al.
Published: (2025)

Ask WhAI:Probing Belief Formation in Role-Primed LLM Agents
by: Moore, Keith, et al.
Published: (2025)

Curveball Steering: The Right Direction To Steer Isn't Always Linear
by: Raval, Shivam, et al.
Published: (2026)

Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
by: Guo, Dongxin, et al.
Published: (2026)

ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports
by: Guluzade, Aynur, et al.
Published: (2025)

Evaluating Large Language Models for IUCN Red List Species Information
by: Uryu, Shinya
Published: (2025)

BioAlchemy: Distilling Biological Literature into Reasoning-Ready Reinforcement Learning Training Data
by: Hsu, Brian, et al.
Published: (2026)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
by: Fadli, Samih
Published: (2025)

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
by: Cho, Seonglae, et al.
Published: (2025)

LLM attribution analysis across different fine-tuning strategies and model scales for automated code compliance
by: Shi, Jack Wei Lun, et al.
Published: (2026)

Categorical Perception in Large Language Model Hidden States: Structural Warping at Digit-Count Boundaries
by: Cacioli, Jon-Paul
Published: (2026)

Assessing Large Language Models on Islamic Legal Reasoning: Evidence from Inheritance Law Evaluation
by: Bouchekif, Abdessalam, et al.
Published: (2025)

The Pragmatic Persona: Discovering LLM Persona through Bridging Inference
by: Yang, Jisoo, et al.
Published: (2026)

Exploring LLM-based Verilog Code Generation with Data-Efficient Fine-Tuning and Testbench Automation
by: Chen, Mu-Chi, et al.
Published: (2026)

When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR)
by: Agarwal, Mahak, et al.
Published: (2025)

Eyla: Toward an Identity-Anchored LLM Architecture with Integrated Biological Priors -- Vision, Implementation Attempt, and Lessons from AI-Assisted Development
by: Aditto, Arif
Published: (2026)

FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification
by: Guo, Dongxin, et al.
Published: (2026)

A Hierarchical Error Framework for Reliable Automated Coding in Communication Research: Applications to Health and Political Communication
by: Zhao, Zhilong, et al.
Published: (2025)

CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systems
by: Sun, Kangkang, et al.
Published: (2026)

Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding
by: Figueiredo, Vanessa
Published: (2025)

In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot Classification
by: Liu, Ming
Published: (2026)

Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
by: Liu, Ming
Published: (2026)

The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models
by: Liu, Ming
Published: (2026)

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
by: Abramov, Roman, et al.
Published: (2025)

Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models
by: Cui, Sasha, et al.
Published: (2025)

Qtok: A Comprehensive Framework for Evaluating Multilingual Tokenizer Quality in Large Language Models
by: Chelombitko, Iaroslav, et al.
Published: (2024)

MoVoC: Morphology-Aware Subword Construction for Geez Script Languages
by: Teklehaymanot, Hailay Kidu, et al.
Published: (2025)

BudgetMem: Learning Selective Memory Policies for Cost-Efficient Long-Context Processing in Language Models
by: Alla, Chandra Vamsi Krishna, et al.
Published: (2025)

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
by: Cho, Seonglae, et al.
Published: (2026)

Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias
by: Wu, Shuai, et al.
Published: (2026)

Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B
by: Cacioli, Jon-Paul
Published: (2026)

Exemplar Retrieval Without Overhypothesis Induction: Limits of Distributional Sequence Learning in Early Word Learning
by: Cacioli, Jon-Paul
Published: (2026)

Align and Shine: Building High-Quality Sentence-Aligned Corpora for Multilingual Text Simplification
by: Hilasaca, Kenji, et al.
Published: (2026)

ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law
by: Shportun, Nazarii
Published: (2026)

Intention Collapse: Intention-Level Metrics for Reasoning in Language Models
by: Vera, Patricio
Published: (2026)

Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs
by: Keeman, Michael
Published: (2026)

KAConvText: Novel Approach to Burmese Sentence Classification using Kolmogorov-Arnold Convolution
by: Thu, Ye Kyaw, et al.
Published: (2025)

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models
by: Young, Richard J.
Published: (2026)

RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences
by: Zhou, Yangyang, et al.
Published: (2026)