Search Results for author:
Found 15 papers, 10 papers with code
Length Desensitization in Direct Preference Optimization
Direct Preference Optimization (DPO) is widely utilized in the Reinforcement Learning from Human Feedback (RLHF) phase to align Large Language Models (LLMs) with human preferences, thereby enhancing both their harmlessness and efficacy.
Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis
Finally, SEA-A introduces a new evaluation metric called mismatch score to assess the consistency between paper contents and reviews.
A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond
Building on our examination of the developmental trajectories, we further investigate the emerging synergies between code intelligence and broader machine intelligence, uncovering new cross-domain opportunities and illustrating the substantial influence of code intelligence across various domains.
Learning to Check: Unleashing Potentials for Self-Correction in Large Language Models
In this paper, we aim to enhance the self-checking capabilities of LLMs by constructing training data for checking tasks.
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
Autonomous interaction with the computer has been a longstanding challenge with great potential, and the recent proliferation of large language models (LLMs) has markedly accelerated progress in building digital agents.
DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models
Chain-of-Thought (CoT) prompting has proven to be effective in enhancing the reasoning capabilities of Large Language Models (LLMs) with at least 100 billion parameters.
Exchanging-based Multimodal Fusion with Transformer
To solve these issues, in this paper, we propose a novel exchanging-based multimodal fusion model MuSE for text-vision fusion based on Transformer.
When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario
In this paper, we introduce gradient descent into black-box tuning scenario through knowledge distillation.
Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives
Large language models (LLMs) have shown increasing power on various natural language processing (NLP) tasks.
Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognition
We design an improved triplet network to map samples and prototype vectors into a low-dimensional space that is easier to be classified and propose an adaptive margin for each entity type.
Meta-Learning Siamese Network for Few-Shot Text Classification
Few-shot learning has been used to tackle the problem of label scarcity in text classification, of which meta-learning based methods have shown to be effective, such as the prototypical networks (PROTO).
SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition
Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data.
Programming Knowledge Tracing: A Comprehensive Dataset and A New Model
More specifically, we construct a bipartite graph for programming problem embedding, and design an improved pre-training model PLCodeBERT for code embedding, as well as a double-sequence RNN model with exponential decay attention for effective feature fusion.
Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance.
Probing bino NLSP at lepton colliders
For a bino mass around 10 GeV, a slepton mass less than 4 TeV (3 TeV) can be probed at the $2\sigma$ ($5\sigma$) level, which is much beyond the reach of the LHC for direct slepton searches.
High Energy Physics - Phenomenology
