Related papers: Rationale-Enhanced Language Models are Better Cont…
Relation extraction (RE) is a sub-discipline of information extraction (IE) which focuses on the prediction of a relational predicate from a natural-language input unit (such as a sentence, a clause, or even a short paragraph consisting of…
Referring Expression Comprehension (REC) aims to localize an image region of a given object described by a natural-language expression. While promising performance has been demonstrated, existing REC algorithms make a strong assumption that…
Modelling a language model for a multi-lingual scenario includes several potential challenges, among which catastrophic forgetting is the major challenge. For example, small language models (SLM) built for low-resource languages by adapting…
Retrieval-augmented generation (RAG) enhances the capabilities of large language models (LLMs) by incorporating external knowledge into their input prompts. However, when the retrieved context contradicts the LLM's parametric knowledge, it…
Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence due to catastrophic forgetting. Large language models (LLMs) are often impractical to frequent…
Relation extraction (RE) aims to identify the semantic relations between named entities in text. Recent years have witnessed it raised to the document level, which requires complex reasoning with entities and mentions throughout an entire…
Large language models (LLMs) are increasingly used in scientific domains. While they can produce reasoning-like content via methods such as chain-of-thought prompting, these outputs are typically unstructured and informal, obscuring whether…
Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty-aware data selection methods attempt to address this by…
Analysing the generalisation capabilities of relation extraction (RE) models is crucial for assessing whether they learn robust relational patterns or rely on spurious correlations. Our cross-dataset experiments find that RE models struggle…
Recent advancements in large language models (LLMs) have shown remarkable progress, yet their ability to solve complex problems remains limited. In this work, we introduce Cumulative Reasoning (CR), a structured framework that enhances LLM…
The continual learning capability of large language models (LLMs) is crucial for advancing artificial general intelligence. However, continual fine-tuning LLMs across various domains often suffers from catastrophic forgetting, characterized…
A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora. In this paper we present a conceptually simple and effective transfer learning approach that addresses the problem of…
Unsupervised relation extraction (URE) aims at discovering underlying relations between named entity pairs from open-domain plain text without prior information on relational distribution. Existing URE models utilizing contrastive learning,…
The goal of dialogue relation extraction (DRE) is to identify the relation between two entities in a given dialogue. During conversations, speakers may expose their relations to certain entities by explicit or implicit clues, such evidences…
Relation extraction (RE) is a fundamental task in information extraction, whose extension to multilingual settings has been hindered by the lack of supervised resources comparable in size to large English datasets such as TACRED (Zhang et…
Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as…
Distant Supervised Relation Extraction (DSRE) is usually formulated as a problem of classifying a bag of sentences that contain two query entities, into the predefined relation classes. Most existing methods consider those relation classes…
Cross-document relation extraction (RE) aims to identify relations between the head and tail entities located in different documents. Existing approaches typically adopt the paradigm of ``\textit{Small Language Model (SLM) + Classifier}''.…
Memory-based approaches have shown strong performance in Continual Relation Extraction (CRE). However, storing examples from previous tasks increases memory usage and raises privacy concerns. Recently, prompt-based methods have emerged as a…
Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on input queries to suppress sensitive outputs, yet this often…