Related papers: Trainable Referring Expression Generation using Ov…
A key distinguishing feature of conversational recommender systems over traditional recommender systems is their ability to elicit user preferences using natural language. Currently, the predominant approach to preference elicitation is to…
Existing sequential recommendation methods rely on large amounts of training data and usually suffer from the data sparsity problem. To tackle this, the pre-training mechanism has been widely adopted, which attempts to leverage large-scale…
Personalization of natural language generation plays a vital role in a large spectrum of tasks, such as explainable recommendation, review summarization and dialog systems. In these tasks, user and item IDs are important identifiers for…
Referring expression segmentation aims to segment an object described by a language expression from an image. Despite the recent progress on this task, existing models tackling this task may not be able to fully capture semantics and visual…
There are individual differences in expressive behaviors driven by cultural norms and personality. This between-person variation can result in reduced emotion recognition performance. Therefore, personalization is an important step in…
We study the problem of generating referring expressions modulo different notions of expressive power. We define the notion of $\+L$-referring expression, for a formal language $\+L$ equipped with a semantics in terms of relational models.…
Referring expression comprehension (REC) aims to localize a target object in an image described by a referring expression phrased in natural language. Different from the object detection task that queried object labels have been…
One of the biggest challenges of end-to-end language generation from meaning representations in dialogue systems is making the outputs more natural and varied. Here we take a large corpus of 50K crowd-sourced utterances in the restaurant…
Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further incorporated into these systems to retrieve more relevant items…
The key of referring expression comprehension lies in capturing the cross-modal visual-linguistic relevance. Existing works typically model the cross-modal relevance in each image, where the anchor object/expression and their positive…
This paper addresses a crucial challenge in retrieval-augmented generation-based relation extractors; the end-to-end training is not applicable to conventional retrieval-augmented generation due to the non-differentiable nature of instance…
In programming by example, users "write" programs by generating a small number of input-output examples and asking the computer to synthesize consistent programs. We consider a challenging problem in this domain: learning regular…
Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG…
Large Language Models (LLMs) struggle with generating reliable outputs due to outdated knowledge and hallucinations. Retrieval-Augmented Generation (RAG) models address this by enhancing LLMs with external knowledge, but often fail to…
Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries…
Deep generative models (DGMs) are data-eager because learning a complex model on limited data suffers from a large variance and easily overfits. Inspired by the classical perspective of the bias-variance tradeoff, we propose regularized…
Large language models (LLMs) often struggle with knowledge intensive NLP tasks, such as answering "Who won the latest World Cup?" because the knowledge they learn during training may be insufficient or outdated. Conditioning generation on…
In this paper, we introduce Reward-RAG, a novel approach designed to enhance the Retrieval-Augmented Generation (RAG) model through Reward-Driven Supervision. Unlike previous RAG methodologies, which focus on training language models (LMs)…
World models are increasingly pivotal in interpreting and simulating the rules and actions of complex environments. Genie, a recent model, excels at learning from visually diverse environments but relies on costly human-collected data. We…
We consider the task of personalizing ASR models while being constrained by a fixed budget on recording speaker-specific utterances. Given a speaker and an ASR model, we propose a method of identifying sentences for which the speaker's…