Search Results for author:
Found 19 papers, 16 papers with code
PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA
Hopefully, the conspicuously higher parameter efficiency can establish PRoLoRA as a resource-friendly alternative to LoRA.
Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
This work explores the integration of diffusion models and Chain-of-Thought (CoT), a well-established technique to improve the reasoning ability in autoregressive language models.
G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
We first analyze the limitations of current Multimodal Large Language Models (MLLMs) in this area: they struggle to accurately comprehending basic geometric elements and their relationships.
Language Versatilists vs. Specialists: An Empirical Revisiting on Multilingual Transfer Ability
First, does multilingual transfer ability exist in English-centric models and how does it compare with multilingual pretrained models?
Generating Data for Symbolic Language with Large Language Models
However, such an approach has primarily been applied to natural language tasks and has not yet been explored for symbolic language tasks with complex structured outputs (e. g., semantic parsing and code generation).
OpenICL: An Open-Source Framework for In-context Learning
However, the implementation of ICL is sophisticated due to the diverse retrieval and inference methods involved, as well as the varying pre-processing requirements for different models, datasets, and tasks.
Compositional Exemplars for In-context Learning
The performance of ICL is highly dominated by the quality of the selected in-context examples.
Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering
Despite the surprising few-shot performance of in-context learning (ICL), it is still a common practice to randomly sample examples to serve as context.
ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback
To improve the quality of dataset synthesis, we propose a progressive zero-shot dataset generation framework, ProGen, which leverages the feedback from the task-specific model to guide the generation of new training data via in-context examples.
Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning
In this paradigm, the synthesized data from the PLM acts as the carrier of knowledge, which is used to train a task-specific model with orders of magnitude fewer parameters than the PLM, achieving both higher performance and efficiency than prompt-based zero-shot learning methods on PLMs.
ZeroGen: Efficient Zero-shot Learning via Dataset Generation
There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs).
A Faster Maximum Cardinality Matching Algorithm with Applications in Machine Learning
In this paper, we present a simplification of a recent algorithm (Lahn and Raghvendra, JoCG 2021) for the maximum cardinality matching problem and describe how a maximum cardinality matching in a $\delta$-disc graph can be computed asymptotically faster than $O(n^{3/2})$ time for any moderately dense point set.
Heterogeneous Graph Neural Networks for Keyphrase Generation
The encoder-decoder framework achieves state-of-the-art results in keyphrase generation (KG) tasks by predicting both present keyphrases that appear in the source document and absent keyphrases that do not.
One2Set: Generating Diverse Keyphrases as a Set
In this work, we propose a new training paradigm One2Set without predefining an order to concatenate the keyphrases.
Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning
In response to this problem, we propose a new fine-grained evaluation metric to improve the RL framework, which considers different granularities: token-level $F_1$ score, edit distance, duplication, and prediction quantities.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one.
Uncertainty-Aware Label Refinement for Sequence Labeling
Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks.
Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features
In order to effectively reduce the impact of non-ideal auxiliary tasks on the main task, we further proposed a novel meta-learning-based multi-task learning approach, which trained the shared hidden layers on auxiliary tasks, while the meta-optimization objective was to minimize the loss on the main task, ensuring that the optimizing direction led to an improvement on the main task.
Re-ID Driven Localization Refinement for Person Search
The state-of-the-art methods train the detector individually, and the detected bounding boxes may be sub-optimal for the following re-ID task.
