Related papers: Extract, Integrate, Compete: Towards Verification …
Vision-language models such as CLIP have shown impressive capabilities in encoding texts and images into aligned embeddings, enabling the retrieval of multimodal data in a shared embedding space. However, these embedding-based models still…
Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the…
Assessing the video comprehension capabilities of multimodal AI systems can effectively measure their understanding and reasoning abilities. Most video evaluation benchmarks are limited to a single language, typically English, and…
Reinforcement learning has emerged as an effective paradigm for training large language models to perform search-augmented reasoning. However, existing approaches rely on trajectory-level rewards that cannot distinguish precise search…
Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…
Contradiction retrieval refers to identifying and extracting documents that explicitly disagree with or refute the content of a query, which is important to many downstream applications like fact checking and data cleaning. To retrieve…
Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy. Prompt selection is critical in VICL, but current methods assume the…
Evidence-based fact checking aims to verify the truthfulness of a claim against evidence extracted from textual sources. Learning a representation that effectively captures relations between a claim and evidence can be challenging. Recent…
Large-scale and high-quality corpora are necessary for evaluating machine reading comprehension models on a low-resource language like Vietnamese. Besides, machine reading comprehension (MRC) for the health domain offers great potential for…
In order to improve the accuracy performance of Chinese text classification models with low hardware requirements, an improved concatenation-based model is designed in this paper, which is a concatenation of 5 different sub-models,…
We present Native Chinese Reader (NCR), a new machine reading comprehension (MRC) dataset with particularly long articles in both modern and classical Chinese. NCR is collected from the exam questions for the Chinese course in China's high…
Fact-checking has gained increasing attention due to the widespread of falsified information. Most fact-checking approaches focus on claims made in English only due to the data scarcity issue in other languages. The lack of fact-checking…
We present a Chinese judicial reading comprehension (CJRC) dataset which contains approximately 10K documents and almost 50K questions with answers. The documents come from judgment documents and the questions are annotated by law experts.…
Chinese Spelling Check (CSC) aims to detect and correct error tokens in Chinese contexts, which has a wide range of applications. However, it is confronted with the challenges of insufficient annotated data and the issue that previous…
Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness…
A lot of prior work on event extraction has exploited a variety of features to represent events. Such methods have several drawbacks: 1) the features are often specific for a particular domain and do not generalize well; 2) the features are…
Document understanding and information extraction include different tasks to understand a document and extract valuable information automatically. Recently, there has been a rising demand for developing document understanding among…
Referring expression comprehension (REF) aims at identifying a particular object in a scene by a natural language expression. It requires joint reasoning over the textual and visual domains to solve the problem. Some popular referring…
Question answering (QA) models for reading comprehension have achieved human-level accuracy on in-distribution test sets. However, they have been demonstrated to lack robustness to challenge sets, whose distribution is different from that…
In settings from fact-checking to question answering, we frequently want to know whether a collection of evidence (premises) entails a hypothesis. Existing methods primarily focus on the end-to-end discriminative version of this task, but…