Wenqiang Lei

Vague Preference Policy Learning for Conversational Recommendation

2023 · arXiv (Cornell University)

Conversational recommendation systems (CRS) commonly assume users have clear preferences, leading to potential over-filtering of relevant alternatives. However, users often exhibit vague, non-binary preferences. We introduce the Vague Preference Multi-round Conversational Recommendation (VPMCR) scenario, employing …

Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective

2024 · arXiv (Cornell University)

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across various tasks, DPO has …

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 …

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

2020

Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models. A successful Conversational Recommender System (CRS) requires proper handling of interactions between conversation and recommendation. …

Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering

2021 · arXiv (Cornell University)

Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents. Recently, there has been a …

KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos

2022 · Proceedings of the 31st ACM International Conference on Information & Knowledge Management

Recommender systems deployed in real-world applications can have inherent exposure bias, which leads to the biased logged data plaguing the researchers. A fundamental way to address this thorny problem is to collect users' interactions on …