Ji-Rong Wen

Scalable Graph Neural Networks via Bidirectional Propagation

2020 · arXiv (Cornell University)

Graph Neural Networks (GNN) is an emerging field for learning on non-Euclidean data. Recently, there has been increased interest in designing GNN that scales to large graphs. Most existing methods use "graph sampling" or "layer-wise …

Pchatbot: A Large-Scale Dataset for Personalized Chatbot

2021

atural language dialogue systems raise great attention recently. As many dialogue models are data-driven, high-quality datasets are essential to these systems. In this paper, we introduce Pchatbot, a large-scale dialogue dataset that contains two subsets …

A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speech

2021 · arXiv (Cornell University)

In this paper, we present a neural model for joint dropped pronoun recovery (DPR) and conversational discourse parsing (CDP) in Chinese conversational speech. We show that DPR and CDP are closely related, and a joint …

Unbiased Sequential Recommendation with Latent Confounders

2022 · Proceedings of the ACM Web Conference 2022

Sequential recommendation holds the promise of understanding user preference by capturing successive behavior correlations. Existing research focus on designing different models for better fitting the offline datasets. However, the observational data may have been contaminated …

There Are a Thousand Hamlets in a Thousand People’s Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Knowledge-grounded conversation (KGC) shows great potential in building an engaging and knowledgeable chatbot, and knowledge selection is a key ingredient in it. However, previous methods for knowledge selection only concentrate on the relevance between knowledge …

A Brief History of Recommender Systems

2022 · arXiv (Cornell University)

Soon after the invention of the Internet, the recommender system emerged and related technologies have been extensively studied and applied by both academia and industry. Currently, recommender system has become one of the most successful …

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models

2023 · arXiv (Cornell University)

The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs), which rely on natural language conversations to satisfy user needs. In this paper, we embark …

SSP: Self-Supervised Post-training for Conversational Search

2023

Conversational search has been regarded as the next-generation search paradigm.Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever.However, these methods, which usually initialize parameters by query reformulation to …

TextBox 2.0: A Text Generation Library with Pre-trained Language Models

2022

Tianyi Tang, Junyi Li, Zhipeng Chen, Yiwen Hu, Zhuohao Yu, Wenxun Dai, Wayne Xin Zhao, Jian-yun Nie, Ji-rong Wen. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2022.

DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy

2023 · arXiv (Cornell University)

Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior studies have focused on modeling reasoning steps using various thought …

Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models

2024 · arXiv (Cornell University)

Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. It remains a challenging problem to explain the underlying mechanisms by which LLMs process multilingual texts. In this …

CL4DIV: A Contrastive Learning Framework for Search Result Diversification

2024

Search result diversification aims to provide a diversified document ranking list so as to cover as many intents as possible and satisfy the various information needs of different users. Existing approaches usually represented documents by …

StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses

2024 · arXiv (Cornell University)

Standard Large Language Models (LLMs) struggle with handling dialogues with long contexts due to efficiency and consistency issues. According to our observation, dialogue contexts are highly structured, and the special token of \textit{End-of-Utterance} (EoU) in …

Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation

2024 · arXiv (Cornell University)

Nowadays, reading or writing comments on captivating videos has emerged as a critical part of the viewing experience on online video platforms. However, existing recommender systems primarily focus on users' interaction behaviors with videos, neglecting …

ICLEval: Evaluating In-Context Learning Ability of Large Language Models

2024 · arXiv (Cornell University)

In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Evaluating the ICL ability of LLMs can enhance their utilization and deepen …

YuLan: An Open-source Large Language Model

2024 · arXiv (Cornell University)

Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many open-source LLMs have been released with technical reports, the lack of training …

Progressive Multimodal Reasoning via Active Retrieval

2024 · arXiv (Cornell University)

Multi-step multimodal reasoning tasks pose significant challenges for multimodal large language models (MLLMs), and finding effective ways to enhance their performance in such scenarios remains an unresolved issue. In this paper, we propose AR-MCTS, a …

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

2025

Retrieval-augmented generation (RAG) has effectively mitigated the hallucination problem of large language models (LLMs). However, the difficulty of aligning the retriever with the LLMs' diverse knowledge preferences inevitably poses a challenge in developing a reliable …

Towards Effective Code-Integrated Reasoning

2025 · arXiv (Cornell University)

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use …

DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation

2025 · arXiv (Cornell University)

Recently, large language models (LLMs) have been introduced into recommender systems (RSs), either to enhance traditional recommendation models (TRMs) or serve as recommendation backbones. However, existing LLM-based RSs often do not fully exploit the complementary …

A Neural Collaborative Filtering Model with Interaction-based Neighborhood

2017

Recently, deep neural networks have been widely applied to recommender systems. A representative work is to utilize deep learning for modeling complex user-item interactions. However, similar to traditional latent factor models by factorizing user-item interactions, …

Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks

2018

With the revival of neural networks, many studies try to adapt powerful sequential neural models, ıe Recurrent Neural Networks (RNN), to sequential recommendation. RNN-based networks encode historical interaction records into a hidden state vector. Although …

Taxonomy-Aware Multi-Hop Reasoning Networks for Sequential Recommendation

2019

In this paper, we focus on the task of sequential recommendation using taxonomy data. Existing sequential recommendation methods usually adopt a single vectorized representation for learning the overall sequential characteristics, and have a limited modeling …

S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization

2020

Recently, significant progress has been made in sequential recommendation with deep learning. Existing neural sequential recommendation models usually rely on the item prediction loss to learn model parameters or data representations. However, the model trained …

Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion

2020

Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. Although several efforts have been made for CRS, two major issues still remain to be solved. First, the conversation data itself …

Towards Topic-Guided Conversational Recommender System

2020

Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. To develop an effective CRS, the support of high-quality datasets is essential. Existing CRS datasets mainly focus on immediate requests from …

Counterfactual Data-Augmented Sequential Recommendation

2021

Sequential recommendation aims at predicting users' preferences based on their historical behaviors. However, this recommendation strategy may not perform well in practice due to the sparsity of the real-world data. In this paper, we propose …

A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions

2021

Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Recently, a large number of studies focus on semantically or syntactically complicated questions. In this paper, we elaborately summarize the …

RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking

2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to …

RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms

2021

In recent years, there are a large number of recommendation algorithms proposed in the literature, from traditional collaborative filtering to deep learning algorithms. However, the concerns about how to standardize open source implementation of recommendation …

Debiased Contrastive Learning of Unsupervised Sentence Representations

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close positive examples to enhance the alignment while push apart irrelevant …

Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning

2022 · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Conversational recommender systems (CRS) aim to proactively elicit user preference and recommend high-quality items through natural language conversations. Typically, a CRS consists of a recommendation module to predict preferred items for users and a conversation …

Towards Universal Sequence Representation Learning for Recommender Systems

2022 · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

In order to develop effective sequential recommenders, a series of sequence representation learning (SRL) methods are proposed to model historical user behaviors. Most existing SRL methods rely on explicit item IDs for developing the sequence …

A Survey of Large Language Models

2026 · Frontiers of Computer Science

Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advanced capabilities, …