Search Results for author: Yequan Wang

Found 22 papers, 7 papers with code

Not all Layers of LLMs are Necessary during Inference

no code implementations4 Mar 2024 Siqi Fan, Xin Jiang, Xiang Li, Xuying Meng, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang, Zhongyuan Wang

To answer this question, we first indicate that Not all Layers are Necessary during Inference by statistically analyzing the activated layers across tasks.

In-Context Learning

Spectral-Based Graph Neural Networks for Complementary Item Recommendation

no code implementations4 Jan 2024 Haitong Luo, Xuying Meng, Suhang Wang, Hanyun Cao, Weiyao Zhang, Yequan Wang, Yujun Zhang

In this study, we present a novel approach called Spectral-based Complementary Graph Neural Networks (SComGNN) that utilizes the spectral properties of complementary item graphs.

Attribute Recommendation Systems

Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis

no code implementations11 Sep 2023 Li Du, Yequan Wang, Xingrun Xing, Yiqun Ya, Xiang Li, Xin Jiang, Xuezhi Fang

Although demonstrating superb performance on various NLP tasks, large language models (LLMs) still suffer from the hallucination problem, which threatens the reliability of LLMs.

Hallucination Instruction Following +2

FLM-101B: An Open LLM and How to Train It with $100K Budget

no code implementations7 Sep 2023 Xiang Li, Yiqun Yao, Xin Jiang, Xuezhi Fang, Xuying Meng, Siqi Fan, Peng Han, Jing Li, Li Du, Bowen Qin, Zheng Zhang, Aixin Sun, Yequan Wang

We demonstrate that a 101B-parameter LLM with 0. 31T tokens can be trained with a budget of 100K US dollars.

Memorization

Rethinking Document-Level Relation Extraction: A Reality Check

no code implementations15 Jun 2023 Jing Li, Yequan Wang, Shuai Zhang, Min Zhang

Recently, numerous efforts have continued to push up performance boundaries of document-level relation extraction (DocRE) and have claimed significant progress in DocRE.

Document-level Relation Extraction Relation

Masked Structural Growth for 2x Faster Language Model Pre-training

1 code implementation4 May 2023 Yiqun Yao, Zheng Zhang, Jing Li, Yequan Wang

In terms of growth schedule, the impact of each single dimension on a schedule's efficiency is under-explored by existing work.

Language Modelling Large Language Model +1

FreeLM: Fine-Tuning-Free Language Model

no code implementations2 May 2023 Xiang Li, Xin Jiang, Xuying Meng, Aixin Sun, Yequan Wang

FreeLM outperforms large models e. g., GPT-3 and InstructGPT, on a range of language understanding tasks in experiments.

Language Modelling

NetGPT: Generative Pretrained Transformer for Network Traffic

no code implementations19 Apr 2023 Xuying Meng, Chungang Lin, Yequan Wang, Yujun Zhang

Pretrained models for network traffic can utilize large-scale raw data to learn the essential characteristics of network traffic, and generate distinguishable results for input traffic without considering specific downstream tasks.

Scheduling Traffic Classification

Research without Re-search: Maximal Update Parametrization Yields Accurate Loss Prediction across Scales

1 code implementation14 Apr 2023 Yiqun Yao, Yequan Wang

As language models scale up, it becomes increasingly expensive to verify research ideas because conclusions on small models do not trivially transfer to large ones.

DialogPaint: A Dialog-based Image Editing Model

no code implementations17 Mar 2023 Jingxuan Wei, Shiyu Wu, Xin Jiang, Yequan Wang

We introduce DialogPaint, a novel framework that bridges conversational interactions with image editing, enabling users to modify images through natural dialogue.

Style Transfer

GCRE-GPT: A Generative Model for Comparative Relation Extraction

no code implementations15 Mar 2023 Yequan Wang, Hengran Zhang, Aixin Sun, Xuying Meng

Given comparative text, comparative relation extraction aims to extract two targets (\eg two cameras) in comparison and the aspect they are compared for (\eg image quality).

Relation Relation Extraction

PoKE: Prior Knowledge Enhanced Emotional Support Conversation with Latent Variable

no code implementations23 Oct 2022 Xiaohan Xu, Xuying Meng, Yequan Wang

Further experiments prove that abundant prior knowledge is conducive to high-quality emotional support, and a well-learned latent variable is critical to the diversity of generations.

Perplexity from PLM Is Unreliable for Evaluating Text Quality

no code implementations12 Oct 2022 Yequan Wang, Jiawen Deng, Aixin Sun, Xuying Meng

Recently, amounts of works utilize perplexity~(PPL) to evaluate the quality of the generated text.

Common Sense Reasoning

CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction

1 code implementation COLING 2022 Yequan Wang, Xiang Li, Aixin Sun, Xuying Meng, Huaming Liao, Jiafeng Guo

CofeNet is able to extract complicated quotations with components of variable lengths and complicated structures.

Chat-Capsule: A Hierarchical Capsule for Dialog-level Emotion Analysis

no code implementations23 Mar 2022 Yequan Wang, Xuying Meng, Yiyi Liu, Aixin Sun, Yao Wang, Yinhe Zheng, Minlie Huang

These models hence are not optimized for dialog-level emotion detection, i. e. to predict the emotion category of a dialog as a whole.

Emotion Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.