相关论文: Finding Support Examples for In-Context Learning

Differentiating relationships between entity pairs with limited labeled instances poses a significant challenge in few-shot relation classification. Representations of textual data extract rich information spanning the domain, entities, and…

Domain shift remains a persistent challenge in deep-learning-based computer vision, often requiring extensive model modifications or large labeled datasets to address. Inspired by human visual perception, which adjusts input quality through…

Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context…

This paper addresses the generation of explanations with visual examples. Given an input sample, we build a system that not only classifies it to a specific category, but also outputs linguistic explanations and a set of visual examples…

Entity summarization has been a prominent task over knowledge graphs. While existing methods are mainly unsupervised, we present DeepLENS, a simple yet effective deep learning model where we exploit textual semantics for encoding triples…

Evidence plays a crucial role in automated fact-checking. When verifying real-world claims, existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. Such methods…

One possible approach to tackle the class imbalance in classification tasks is to resample a training dataset, i.e., to drop some of its elements or to synthesize new ones. There exist several widely-used resampling methods. Recent research…

Despite enormous progress in object detection and classification, the problem of incorporating expected contextual relationships among object instances into modern recognition systems remains a key challenge. In this work we propose…

In language processing, training data with extremely large variance may lead to difficulty in the language model's convergence. It is difficult for the network parameters to adapt sentences with largely varied semantics or grammatical…

A limitation of modern document retrieval embedding methods is that they typically encode passages (chunks) from the same documents independently, often overlooking crucial contextual information from the rest of the document that could…

While recent pre-trained transformer-based models can perform named entity recognition (NER) with great accuracy, their limited range remains an issue when applied to long documents such as whole novels. To alleviate this issue, a solution…

Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Using context can help, both for unseen and ambiguous words. Yet most context-sensitive approaches require full…

In recent years, the rise of large language models (LLMs) has made it possible to directly achieve named entity recognition (NER) without any demonstration samples or only using a few samples through in-context learning (ICL). However,…

Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an instruction data selection framework based on weighted in-context influence (wICI),…

Training vision-language models via instruction tuning relies on large data mixtures spanning diverse tasks and domains, yet these mixtures frequently include redundant information that increases computational costs without proportional…

Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context. However, the…

Combining a pretrained language model (PLM) with textual patterns has been shown to help in both zero- and few-shot settings. For zero-shot performance, it makes sense to design patterns that closely resemble the text seen during…

Multimodal Large Language Models (MLLMs) adapt to visual tasks via in-context learning (ICL), which relies heavily on demonstration quality. The dominant demonstration selection strategy is unsupervised k-Nearest Neighbor (kNN) search.…

Large language models (LLMs) have shown an impressive ability to perform a wide range of tasks using in-context learning (ICL), where a few examples are used to describe a task to the model. However, the performance of ICL varies…

In-context learning is the paradigm that adapts large language models to downstream tasks by providing a few examples. Few-shot selection -- selecting appropriate examples for each test instance separately -- is important for in-context…