Search Results for author:
Found 10 papers, 4 papers with code
Sparse Orthogonal Parameters Tuning for Continual Learning
We hypothesize that the effectiveness of SoTU lies in the transformation of knowledge learned from multiple domains into the fusion of orthogonal delta parameters.
Is Parameter Collision Hindering Continual Learning in LLMs?
Large Language Models (LLMs) often suffer from catastrophic forgetting when learning multiple tasks sequentially, making continual learning (CL) essential for their dynamic deployment.
Bidirectional Uncertainty-Based Active Learning for Open Set Annotation
In this paper, we attempt to query examples that are both likely from known classes and highly informative, and propose a Bidirectional Uncertainty-based Active Learning (BUAL) framework.
PiCO: Peer Review in LLMs based on the Consistency Optimization
Existing large language models (LLMs) evaluation methods typically focus on testing the performance on some closed-environment and domain-specific benchmarks with human annotations.
LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples
This phenomenon forces us to revisit that \emph{hallucination may be another view of adversarial examples}, and it shares similar characteristics with conventional adversarial examples as a basic property of LLMs.
Towards Better Query Classification with Multi-Expert Knowledge Condensation in JD Ads Search
To overcome this challenge, in this paper, we propose knowledge condensation (KC), a simple yet effective knowledge distillation framework to boost the classification performance of the online FastText model under strict low latency constraints.
Active Learning for Open-set Annotation
To tackle this open-set annotation (OSA) problem, we propose a new active learning framework called LfOSA, which boosts the classification performance with an effective sampling strategy to precisely detect examples from known classes for annotation.
Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries
Recently, much research has been devoted to improving the model robustness by training with noise perturbations.
Co-Imitation Learning without Expert Demonstration
Imitation learning is a primary approach to improve the efficiency of reinforcement learning by exploiting the expert demonstrations.
Reinforcement Learning with Supervision from Noisy Demonstrations
In this paper, we propose a novel framework to adaptively learn the policy by jointly interacting with the environment and exploiting the expert demonstrations.
