Search Results - Cheng Lu
-
1
Trends and Volatilities in Heterogeneous Patent Quality in Taiwan
Published 2009Fuente: RedalycTipo de material: Artículo científicoAcceso al recurso -
2
Understanding the ultraspherical spectral method
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
3
Robust Uncertainty Quantification for Self-Evolving Large Language Models via Continual Domain Pretraining
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
4
Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts
Published 2026Fuente: arXivTipo de material: PreprintAcceso al recurso -
5
Revisiting NLI: Towards Cost-Effective and Human-Aligned Metrics for Evaluating LLMs in Question Answering
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
6
JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
7
Conformalized Link Prediction on Graph Neural Networks
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
8
A new banded Petrov--Galerkin spectral method
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
9
Shakespearean Sparks: The Dance of Hallucination and Creativity in LLMs' Decoding Layers
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
10
Credence Calibration Game? Calibrating Large Language Models through Structured Play
Published 2025Fuente: arXivTipo de material: PreprintAcceso al recurso -
11
TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning
Published 2026Fuente: arXivTipo de material: PreprintAcceso al recurso -
12
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
Published 2026Fuente: arXivTipo de material: PreprintAcceso al recurso -
13
When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification
Published 2026Fuente: arXivTipo de material: PreprintAcceso al recurso -
14
Differentiable Conformal Training for LLM Reasoning Factuality
Published 2026Fuente: arXivTipo de material: PreprintAcceso al recurso -
15
Unveiling Performance Challenges of Large Language Models in Low-Resource Healthcare: A Demographic Fairness Perspective
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
16
A Survey on Safe Multi-Modal Learning System
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
17
API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
18
LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
19
Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso -
20
Conformal Prediction: A Data Perspective
Published 2024Fuente: arXivTipo de material: PreprintAcceso al recurso