Related papers: eTracer: Towards Traceable Text Generation via Cla…
Tactile sensation plays a crucial role in the development of multi-modal large models and embodied intelligence. To collect tactile data with minimal cost as possible, a series of studies have attempted to generate tactile images by…
Creating an essay based on a few given topics is a challenging NLP task. Although several effective methods for this problem, topic-to-essay generation, have appeared recently, there is still much room for improvement, especially in terms…
Retrieval-augmented generation (RAG) faces challenges related to factual correctness, source attribution, and response completeness. To address them, we propose a modular pipeline for grounded response generation that operates on…
We introduce a language generative model framework for generating a styled paragraph based on a context sentence and a style reference example. The framework consists of a style encoder and a texts decoder. The style encoder extracts a…
Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar…
New systems employ Machine Learning to sift through large knowledge sources, creating flexible Large Language Models. These models discern context and predict sequential information in various communication forms. Generative AI, leveraging…
Retrieval augmented generation mitigates limitations of large language models in factual consistency and knowledge updating by introducing external knowledge. However, practical applications still suffer from semantic misalignment between…
Data-to-text generation models face challenges in ensuring data fidelity by referring to the correct input source. To inspire studies in this area, Wiseman et al. (2017) introduced the RotoWire corpus on generating NBA game summaries from…
Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…
3D visual grounding is the ability to localize objects in 3D scenes conditioned by utterances. Most existing methods devote the referring head to localize the referred object directly, causing failure in complex scenarios. In addition, it…
Recent work in neural generation has attracted significant interest in controlling the form of text, such as style, persona, and politeness. However, there has been less work on controlling neural text generation for content. This paper…
We introduce Texygen, a benchmarking platform to support research on open-domain text generation models. Texygen has not only implemented a majority of text generation models, but also covered a set of metrics that evaluate the diversity,…
While new technologies are expected to revolutionise and become game-changers in improving the efficiencies and practises of our daily lives, it is also critical to investigate and understand the barriers and opportunities faced by their…
We introduce AccurateRAG -- a novel framework for constructing high-performance question-answering applications based on retrieval-augmented generation (RAG). Our framework offers a pipeline for development efficiency with tools for raw…
Fact verification (FV) is a challenging task which aims to verify a claim using multiple evidential sentences from trustworthy corpora, e.g., Wikipedia. Most existing approaches follow a three-step pipeline framework, including document…
The second edition of the TREC Retrieval Augmented Generation (RAG) Track advances research on systems that integrate retrieval and generation to address complex, real-world information needs. Building on the foundation of the inaugural…
Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is necessary for a correct answer. Existing dynamic early-exit…
Recent agentic search frameworks enable deep research via iterative planning and retrieval, reducing hallucinations and enhancing factual grounding. However, they remain text-centric, overlooking the multimodal evidence that characterizes…
Traditional conversational travel recommender systems primarily optimize for user relevance and convenience, often reinforcing popular, overcrowded destinations and carbon-intensive travel choices. To address this, we present TRACE (Tourism…
We study causal discovery from a single observed sequence of discrete events generated by a stochastic process, as encountered in vehicle logs, manufacturing systems, or patient trajectories. This regime is particularly challenging due to…