conftrace_

linear probing

48 papers

Explore in graph

Also known as

LP

Co-occurring keywords

representation learning (6206) large language model (13587) transfer learning (5449) self-supervised learning (3777) domain adaptation (4595) numerical reasoning (145) linear probe (27) vision-language model (2348) low-rank adaptation (560) distribution shift (722)

Papers

LatentGate: Low-Latency Semantic Routing via Frozen-Backbone Probing of Small Language Models ACL 2026
Measuring and Mitigating Shortcut Reliance in Language Models with Probe-Based Representation Entanglement ACL 2026
Rhetorical Questions in LLM Representations: A Linear Probing Study ACL 2026
Beyond Transcription: Mechanistic Interpretability in ASR AAAI 2026
LLM Safety From Within: Detecting Harmful Content with Internal Representations ACL 2026
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering EACL 2026
Not Just a Piece of Cake: Cross-Lingual Fine-Tuning for Idiom Identification IJCNLP 2025
Universal Backdoor Defense via Label Consistency in Vertical Federated Learning IJCAI 2025
Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding CVPR 2025
Sonata: Self-Supervised Learning of Reliable Point Representations CVPR 2025
LP-FT-LoRA: A Three-Stage PEFT Framework for Efficient Domain Adaptation in Bangla NLP Tasks AACL 2025
PentaML at BLP-2025 Task 1: Linear Probing of Pre-trained Transformer-based Models for Bangla Hate Speech Detection AACL 2025
Detecting Hallucination in Large Language Models Through Deep Internal Representation Analysis IJCAI 2025
Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations EMNLP 2025
“I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025
Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models AACL 2025
Not Just a Piece of Cake: Cross-Lingual Fine-Tuning for Idiom Identification AACL 2025
LP-FT-LoRA: A Three-Stage PEFT Framework for Efficient Domain Adaptation in Bangla NLP Tasks IJCNLP 2025
PentaML at BLP-2025 Task 1: Linear Probing of Pre-trained Transformer-based Models for Bangla Hate Speech Detection IJCNLP 2025
Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs EMNLP 2025
Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes ACL 2025
How Not to Stitch Representations to Measure Similarity: Task Loss Matching Versus Direct Matching AAAI 2025
Linear Decoding of Morphology Relations in Language Models (Student Abstract) AAAI 2025
Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models IJCNLP 2025
Causal language modeling can elicit search and reasoning capabilities on logic puzzles NIPS 2024