Related papers: ConsistentEE: A Consistent and Hardness-Guided Ear…

Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models,…

Reasoning models have demonstrated exceptional performance in tasks such as mathematics and logical reasoning, primarily due to their ability to engage in step-by-step thinking during the reasoning process. However, this often leads to…

Recent work shows that in-context learning and optimization of in-context examples (ICE) can significantly improve the accuracy of large language models (LLMs) on a wide range of tasks, leading to an apparent consensus that ICE optimization…

Inference is a versatile tool that underlies scientific discovery, machine learning, and everyday decision-making: it describes how an agent updates a probability distribution as partial information is acquired from multiple measurements,…

Pre-training and then fine-tuning large language models is commonly used to achieve state-of-the-art performance in natural language processing (NLP) tasks. However, most pre-trained models suffer from low inference speed. Deploying such…

Recently, pre-trained models have achieved state-of-the-art results in various language understanding tasks, which indicates that pre-training on large-scale corpora may play a crucial role in natural language processing. Current…

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…

In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural networks are known to suffer under this setting, as they forget previously acquired…

This paper proposes a novel training method to improve the robustness of Extractive Question Answering (EQA) models. Previous research has shown that existing models, when trained on EQA datasets that include unanswerable questions,…

Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts. Most existing methods assume that events appear in sentences without overlaps, which are not applicable to the complicated…

Large language models (LLMs) require iterative updates to address the outdated information problem, where LLM unlearning offers an approach for selective removal. However, mainstream unlearning methods primarily rely on fine-tuning…

Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language models (LLMs). They still suffer from catastrophic forgetting (CF). Little work has been done to exploit in-context learning (ICL) to leverage…

In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, there is no comparably principled basis to justify trust in the content of the text…

Deep neural networks (DNNs) have made significant progress in recognizing visual elements and generating descriptive text in image-captioning tasks. However, their improved performance comes from increased computational burden and inference…

We propose continual instance learning - a method that applies the concept of continual learning to the task of distinguishing instances of the same object category. We specifically focus on the car object, and incrementally learn to…

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…

Continual Test-Time Adaptation (CTTA) aims to adapt a source pre-trained model to continually changing target domains during inference. As a fundamental principle, an ideal CTTA method should rapidly adapt to new domains (exploration) while…

Prompt optimization automatically refines prompting expressions, unlocking the full potential of LLMs in downstream tasks. However, current prompt optimization methods are costly to train and lack sufficient interpretability. This paper…

Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where…

The cross entropy loss is widely used due to its effectiveness and solid theoretical grounding. However, as training progresses, the loss tends to focus on hard to classify samples, which may prevent the network from obtaining gains in…