Related papers: CUP: Curriculum Learning based Prompt Tuning for I…

Extractive Question Answering (EQA) is one of the most important tasks in Machine Reading Comprehension (MRC), which can be solved by fine-tuning the span selecting heads of Pre-trained Language Models (PLMs). However, most existing…

Prompt learning has recently attracted much attention for adapting pre-trained vision-language models (e.g., CLIP) to downstream recognition tasks. However, most of the existing CLIP-based prompt learning methods only show a limited ability…

While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, understanding and validating their knowledge utilization remains challenging. Chain-of-thought (CoT) prompting partially addresses this by revealing…

For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective. Too often, the litany of proposed explainable deep learning…

Recent advancements in Contrastive Language-Image Pre-training (CLIP) have demonstrated notable success in self-supervised representation learning across various tasks. However, the existing CLIP-like approaches often demand extensive GPU…

Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strategies for scoring item difficulty rely on indirect proxy…

We study the problem of event extraction from text data, which requires both detecting target event types and their arguments. Typically, both the event detection and argument detection subtasks are formulated as supervised sequence…

Script Event Prediction (SEP) aims to predict the subsequent event for a given event chain from a candidate list. Prior research has achieved great success by integrating external knowledge to enhance the semantics, but it is laborious to…

Event extraction is an Information Retrieval task that commonly consists of identifying the central word for the event (trigger) and the event's arguments. This task has been extensively studied for English but lags behind for Portuguese,…

Large Language Models (LLMs) show remarkable potential for few-shot information extraction (IE), yet their performance is highly sensitive to the choice of in-context examples. Conventional selection strategies often fail to provide…

Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than…

Prompt design is a primary control interface for large language models (LLMs), yet standard evaluations largely reduce performance to answer correctness, obscuring why a prompt succeeds or fails and providing little actionable guidance. We…

Instruction tuning improves the performance of large language models (LLMs), but it heavily relies on high-quality training data. Recently, LLMs have been used to synthesize instruction data using seed question-answer (QA) pairs. However,…

Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt…

In this paper, we describe our shared task submissions for Subtask 2 in CASE-2022, Event Causality Identification with Casual News Corpus. The challenge focused on the automatic detection of all cause-effect-signal spans present in the…

Recently, prompt tuning \cite{lester2021power} has gradually become a new paradigm for NLP, which only depends on the representation of the words by freezing the parameters of pre-trained language models (PLMs) to obtain remarkable…

Though CLIP-based prompt tuning significantly enhances pre-trained Vision-Language Models, existing research focuses on reconstructing the model architecture, e.g., additional loss calculation and meta-networks. These approaches generally…

Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce…

Factual knowledge extraction aims to explicitly extract knowledge parameterized in pre-trained language models for application in downstream tasks. While prior work has been investigating the impact of supervised fine-tuning data on the…

This study explores the capability of Large Language Models (LLMs) to evaluate causality in causal graphs generated by conventional statistical causal discovery methods-a task traditionally reliant on manual assessment by human subject…