Search Results for author:
Found 17 papers, 5 papers with code
Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
We find that a small subset of ``cherry'' parameters exhibit a disproportionately large influence on model performance, while the vast majority of parameters have minimal impact.
Who Said That? Benchmarking Social Media AI Detection
Addressing these challenges, this paper introduces SAID (Social media AI Detection), a novel benchmark developed to assess AI-text detection models' capabilities in real social media platforms.
Ada-Instruct: Adapting Instruction Generators for Complex Reasoning
Generating diverse and sophisticated instructions for downstream tasks by Large Language Models (LLMs) is pivotal for advancing the effect.
Evade ChatGPT Detectors via A Single Space
Existing detectors are built upon the assumption that there are distributional gaps between human-generated and AI-generated text.
Exploring Automatically Perturbed Natural Language Explanations in Relation Extraction
Previous research has demonstrated that natural language explanations provide valuable inductive biases that guide models, thereby improving the generalization ability and data efficiency.
Free Lunch for Efficient Textual Commonsense Integration in Language Models
One key observation is that the upper bound of batch partitioning can be reduced to the classic {\it graph k-cut problem}.
Instance-based Learning for Knowledge Base Completion
In this paper, we propose a new method for knowledge base completion (KBC): instance-based learning (IBL).
Open Rule Induction
One weakness of the previous rule induction systems is that they only find rules within a knowledge base (KB) and therefore cannot generalize to more open and complex real-world rules.
Enhancing Natural Language Representation with Large-Scale Out-of-Domain Commonsense
In this paper, we propose to use large-scale out-of-domain commonsense to enhance text representation.
Isotonic Data Augmentation for Knowledge Distillation
However, we found critical order violations between hard labels and soft labels in augmented samples.
Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning
MACD forces the decoupled text encoder to represent the visual information via contrastive learning.
Robust Natural Language Representation Learning for Natural Language Inference by Projecting Superficial Words out
In natural language inference, the semantics of some words do not affect the inference.
Attention over Phrases
Besides representing the words of the sentence, we introduce hypernodes to represent the candidate phrases in attention.
Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement
In order to distill diverse knowledge from different trained (teacher) models, we propose to use adversarial-based learning strategy where we define a block-wise training loss to guide and optimize the predefined student network to recover the knowledge in teacher models, and to promote the discriminator network to distinguish teacher vs. student features simultaneously.
KBQA: Learning Question Answering over QA Corpora and Knowledge Bases
Based on these templates, our QA system KBQA effectively supports binary factoid questions, as well as complex questions which are composed of a series of binary factoid questions.
Verb Pattern: A Probabilistic Semantic Representation on Verbs
In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb.
