Zhaochun Ren

Dynamic Graph Neural Networks

2018 · arXiv (Cornell University)

Graphs, which describe pairwise relations between objects, are essential representations of many real-world data such as social networks. In recent years, graph neural networks, which extend the neural network models to graph data, have attracted …

Meaningful Answer Generation of E-Commerce Question-Answering

2020 · arXiv (Cornell University)

In e-commerce portals, generating answers for product-related questions has become a crucial task. In this paper, we focus on the task of product-aware answer generation, which learns to generate an accurate and complete answer from …

Contrastive Learning Reduces Hallucination in Conversations

2022 · arXiv (Cornell University)

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking statements that are irrelevant …

DiQAD: A Benchmark Dataset for Open-domain Dialogue Quality Assessment

2023

Dialogue assessment plays a critical role in the development of open-domain dialogue systems. Existing work are uncapable of providing an end-to-end and human-epistemic assessment dataset, while they only provide sub-metrics like coherence or the dialogues …

Answer Retrieval in Legal Community Question Answering

2024 · arXiv (Cornell University)

The task of answer retrieval in the legal domain aims to help users to seek relevant legal advice from massive amounts of professional responses. Two main challenges hinder applying existing answer retrieval approaches in other …

On Protecting the Data Privacy of Large Language Models (LLMs): A Survey

2024 · arXiv (Cornell University)

Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. They learn language patterns by analyzing large amounts of text data, allowing them to perform writing, conversation, summarizing …

Generative Retrieval as Multi-Vector Dense Retrieval

2024 · arXiv (Cornell University)

Generative retrieval generates identifiers of relevant documents in an end-to-end manner using a sequence-to-sequence architecture for a given query. The relation between generative retrieval and other retrieval methods, especially those based on matching within dense …

Disentangling ID and Modality Effects for Session-based Recommendation

2024

Session-based recommendation aims to predict intents of anonymous users based on their limited behaviors. Modeling user behaviors involves two distinct rationales: co-occurrence patterns reflected by item IDs, and fine-grained preferences represented by item modalities (e.g., …

Cognitive Biases in Large Language Models for News Recommendation

2024 · arXiv (Cornell University)

Despite large language models (LLMs) increasingly becoming important components of news recommender systems, employing LLMs in such systems introduces new risks, such as the influence of cognitive biases in LLMs. Cognitive biases refer to systematic …

Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers

2025

Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques. However, effectively enabling LLMs to seek accurate knowledge in complex tasks remains a challenge due to the complexity of multi-hop …

Salience Estimation via Variational Auto-Encoders for Multi-Document Summarization

2017 · Proceedings of the AAAI Conference on Artificial Intelligence

We propose a new unsupervised sentence salience framework for Multi-Document Summarization (MDS), which can be divided into two components: latent semantic modeling and salience estimation. For latent semantic modeling, a neural generative model called Variational …

Neural Rating Regression with Abstractive Tips Generation for Recommendation

2017

Recently, some E-commerce sites launch a new interaction box called Tips on their mobile apps. Users can express their experience and feelings or provide suggestions using short texts typically several words or one sentence. In …

Hierarchical Variational Memory Network for Dialogue Generation

2018

Dialogue systems help various real applications interact with humans in an intelligent natural way. In dialogue systems, the task of dialogue generation aims to generate utterances given previous utterances as contexts. Among various spectrums of …

Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures

2018

Existing solutions to task-oriented dialogue systems follow pipeline designs which introduce architectural complexity and fragility. We propose a novel, holistic, extendable framework based on a single sequence-to-sequence (seq2seq) model which can be optimized with supervised …

Knowledge Diffusion for Neural Dialogue Generation

2018

End-to-end neural dialogue generation has shown promising results recently, but it does not employ knowledge to guide the generation and hence tends to generate short, general, and meaningless responses. In this paper, we propose a …

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 …

RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-Based Recommendation

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

Recurrent neural networks for session-based recommendation have attracted a lot of attention recently because of their promising performance. repeat consumption is a common phenomenon in many recommendation scenarios (e.g., e-commerce, music, and TV program recommendations), …

Neural Attentive Session-based Recommendation

2017

Given e-commerce scenarios that user profiles are invisible, session-based recommendation is proposed to generate recommendation results from short sessions. Previous work only considers the user's sequential behavior in the current session, whereas the user's main …

Mixed Information Flow for Cross-Domain Sequential Recommendations

2022 · ACM Transactions on Knowledge Discovery from Data

Cross-domain sequential recommendation is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One of the key challenges in cross-domain …