Search Results for author:
Found 37 papers, 18 papers with code
GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning
From this observation, we use mutual learning to improve BERT’s early exiting performances, that is, we ask each exit of a multi-exit BERT to distill knowledge from each other.
A Unified Encoding of Structures in Transition Systems
Transition systems usually contain various dynamic structures (e. g., stacks, buffers).
Word Reordering for Zero-shot Cross-lingual Structured Prediction
Adapting word order from one language to another is a key problem in cross-lingual structured prediction.
Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction
Event detection is a classic natural language processing task.
paht_nlp @ MEDIQA 2021: Multi-grained Query Focused Multi-Answer Summarization
First a RoBERTa model is first applied to give a local ranking of the candidate sentences.
Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks
Ensuring safety alignment has become a critical requirement for large language models (LLMs), particularly given their widespread deployment in real-world applications.
Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation
To address these challenges, we introduce HDCEval, a Hierarchical Divide-and-Conquer Evaluation framework tailored for fine-grained alignment in medical evaluation.
NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning
The core of our framework is first to construct a safety reference model from an initially aligned model to amplify safety-related features in neurons.
ACE-$M^3$: Automatic Capability Evaluator for Multimodal Medical Models
As multimodal large language models (MLLMs) gain prominence in the medical field, the need for precise evaluation methods to assess their effectiveness has become critical.
Typicalness-Aware Learning for Failure Detection
We observe that, with the cross-entropy loss, model predictions are optimized to align with the corresponding labels via increasing logit magnitude or refining logit direction.
Online Convex Optimization with Memory and Limited Predictions
The second subroutine is a zeroth-order method that can be used to solve general convex optimization problems with a linear convergence rate that matches the best achievable rate of first-order methods for convex optimization.
Generation with Dynamic Vocabulary
The dynamic vocabulary can be deployed in a plug-and-play way, thus is attractive for various downstream applications.
A Survey of Spatio-Temporal EEG data Analysis: from Models to Applications
In recent years, the field of electroencephalography (EEG) analysis has witnessed remarkable advancements, driven by the integration of machine learning and artificial intelligence.
TS-HTFA: Advancing Time Series Forecasting via Hierarchical Text-Free Alignment with Large Language Models
Given the significant potential of large language models (LLMs) in sequence modeling, emerging studies have begun applying them to time-series forecasting.
TCMBench: A Comprehensive Benchmark for Evaluating Large Language Models in Traditional Chinese Medicine
To address this research gap, we introduce TCM-Bench, an comprehensive benchmark for evaluating LLM performance in TCM.
IAPT: Instruction-Aware Prompt Tuning for Large Language Models
Thus, we propose to learn the idiosyncratic activation functions for prompt generators automatically with the help of rational functions.
A safety realignment framework via subspace-oriented model fusion for large language models
We validate that our safety realignment framework satisfies the safety requirements of a single fine-tuned model as well as multiple models during their fusion.
Multi-Label Out-of-Distribution Detection with Spectral Normalized Joint Energy
Our findings indicate that the application of spectral normalization to joint energy scores notably amplifies the model's capability for OOD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Length Generalization of Causal Transformers without Position Encoding
Generalizing to longer sentences is important for recent Transformer-based language models.
Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models
In this paper, we propose fine-grained detoxification via instance-level prefixes (FGDILP) to mitigate toxic text without additional cost.
Complementary Information Mutual Learning for Multimodality Medical Image Segmentation
CIML adopts the idea of addition and removes inter-modal redundant information through inductive bias-driven task decomposition and message passing-based redundancy filtering.
Text2MDT: Extracting Medical Decision Trees from Medical Texts
In this work, we propose a novel task, Text2MDT, to explore the automatic extraction of MDTs from medical texts such as medical guidelines and textbooks.
Overview of the PromptCBLUE Shared Task in CHIP2023
Many teams from both the industry and academia participated in the shared tasks, and the top teams achieved amazing test results.
PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain
Biomedical language understanding benchmarks are the driving forces for artificial intelligence applications with large language model (LLM) back-ends.
Unified Demonstration Retriever for In-Context Learning
To train UDR, we cast various tasks' training signals into a unified list-wise ranking formulation by language model's feedback.
Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation
In this paper, we propose a simple but effective method called "Candidate Soups," which can obtain high-quality translations while maintaining the inference speed of NAT models.
Forgetting Fast in Recommender Systems
In this paper, we investigate fast machine unlearning techniques for recommender systems that can remove the effect of a small amount of training data from the recommendation model without incurring the full cost of retraining.
Micro-Behavior Encoding for Session-based Recommendation
Specifically, we identify two different patterns of micro-behaviors: "sequential patterns" and "dyadic relational patterns".
Community Trend Prediction on Heterogeneous Graph in E-commerce
In online shopping, ever-changing fashion trends make merchants need to prepare more differentiated products to meet the diversified demands, and e-commerce platforms need to capture the market trend with a prophetic vision.
Discovering Better Model Architectures for Medical Query Understanding
In developing an online question-answering system for the medical domains, natural language inference (NLI) models play a central role in question matching and intention detection.
Fair Differential Privacy Can Mitigate the Disparate Impact on Model Accuracy
This paper proposes a fair differential privacy algorithm (FairDP) to mitigate the disparate impact on model accuracy for each class.
RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
In this library, we implement 73 recommendation models on 28 benchmark datasets, covering the categories of general recommendation, sequential recommendation, context-aware recommendation and knowledge-based recommendation.
AutoTrans: Automating Transformer Design via Reinforced Architecture Search
Though the transformer architectures have shown dominance in many natural language understanding tasks, there are still unsolved issues for the training of transformer models, especially the need for a principled way of warm-up which has shown importance for stable training of a transformer, as well as whether the task at hand prefer to scale the attention product or not.
Sequential Recommender via Time-aware Attentive Memory Network
Recommendation systems aim to assist users to discover most preferred contents from an ever-growing corpus of items.
Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network
Given a set of symptoms to treat, we aim to generate an overall syndrome representation by effectively fusing the embeddings of all the symptoms in the set, to mimic how a doctor induces the syndromes.
Probabilistic Verb Selection for Data-to-Text Generation
In data-to-text Natural Language Generation (NLG) systems, computers need to find the right words to describe phenomena seen in the data.
Quantitative Analysis of Particles Segregation
Then, the whole picture of particles is splintered to small rectangles with the same shape.
