相关论文: UniArk: Improving Generalisation and Consistency f…

Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting…

By retrieving contexts from knowledge graphs, graph-based retrieval-augmented generation (GraphRAG) enhances large language models (LLMs) to generate quality answers for user questions. Many GraphRAG methods have been proposed and reported…

Language technologies that accurately model the dynamics of events must perform commonsense reasoning. Existing work evaluating commonsense reasoning focuses on making inferences about common, everyday situations. To instead investigate the…

Existing deepfake detection techniques struggle to keep-up with the ever-evolving novel, unseen forgeries methods. This limitation stems from their reliance on statistical artifacts learned during training, which are often tied to specific…

Assessing response quality to instructions in language models is vital but challenging due to the complexity of human language across different contexts. This complexity often results in ambiguous or inconsistent interpretations, making…

We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment…

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

Question answering models commonly have access to two sources of "knowledge" during inference time: (1) parametric knowledge - the factual knowledge encoded in the model weights, and (2) contextual knowledge - external knowledge (e.g., a…

Traditional machine learning relies on explicit models and domain assumptions, limiting flexibility and interpretability. We introduce a model-free framework using surprisal (information theoretic uncertainty) to directly analyze and…

Pre-trained Language Models (PLMs) are trained on vast unlabeled data, rich in world knowledge. This fact has sparked the interest of the community in quantifying the amount of factual knowledge present in PLMs, as this explains their…

Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…

Instruction tuning (IT) achieves impressive zero-shot generalization results by training large language models (LLMs) on a massive amount of diverse tasks with instructions. However, how to select new tasks to improve the performance and…

Model compression is increasingly essential for deploying large language models (LLMs), yet existing comparative studies largely focus on pruning and quantization evaluated primarily on knowledge-centric benchmarks. Thus, we introduce…

Uncertainty estimation (UE) aims to detect hallucinated outputs of large language models (LLMs) to improve their reliability. However, UE metrics often exhibit unstable performance across configurations, which significantly limits their…

Misinformation such as fake news is one of the big challenges of our society. Research on automated fact-checking has proposed methods based on supervised learning, but these approaches do not consider external evidence apart from labeled…

Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training.…

We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training. To do so we propose a combination of multitask supervised pretraining on up to 93 tasks designed to…

Universal Dependencies (UD), while widely regarded as the most successful linguistic framework for cross-lingual syntactic representation, remains underexplored in terms of its effectiveness. This paper addresses this gap by integrating UD…

Recommender systems are seen as an effective tool to address information overload, but it is widely known that the presence of various biases makes direct training on large-scale observational data result in sub-optimal prediction…

Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-task language checkers based on their latent representations…