Low-rank adaptation (LoRA) has been developed as an efficient approach for adapting large language models (LLMs) by fine-tuning two low-rank matrices, thereby reducing the number of trainable parameters. However, prior research indicates that many of the weights in these matrices are redundant, leading to inefficiencies in parameter utilization. To address this limitation, we introduce Dense Low-Rank Adaptation (DenseLoRA), a novel approach that enhances parameter efficiency while achieving superior performance compared to LoRA. DenseLoRA builds upon the concept of representation fine-tuning, incorporating a single Encoder-Decoder to refine and compress hidden representations across all adaptation layers before applying adaptation. Instead of relying on two redundant low-rank matrices as in LoRA, DenseLoRA adapts LLMs through a dense low-rank matrix, improving parameter utilization and adaptation efficiency. We evaluate DenseLoRA on various benchmarks, showing that it achieves 83.8% accuracy with only 0.01% of trainable parameters, compared to LoRA’s 80.8% accuracy with 0.70% of trainable parameters on LLaMA3-8B. Additionally, we conduct extensive experiments to systematically assess the impact of DenseLoRA’s components on overall model performance.

Event causality identification (ECI) is a challenging task that involves predicting causal relationships between events in text. Existing prompt-learning-based methods typically concatenate in-context examples only at the input layer, this shallow integration limits the model’s ability to capture the abstract semantic cues necessary for identifying complex causal relationships. To address this limitation, we propose a novel model called Deep In-Context Prompt (DICP), which injects in-context examples into the deeper layer of a pre-trained language model (PLM). This strategy enables the model to leverage the hierarchical semantic representations formed in deeper layers, thereby enhancing its capacity to learn high-level causal abstractions. Moreover, DICP introduces a multi-layer prompt injection mechanism, distributing diverse in-context examples across multiple transformer layers. This design allows the model to recognize a broader range of causal patterns and improves its generalization across different contexts. We evaluate the DICP model through extensive experiments on two widely used datasets, demonstrating its significant improvement in ECI performance compared to existing approaches. Furthermore, we explore the impact of varying the number of deep layers on performance, providing valuable insights into the optimal layer configuration for ECI tasks.

Large Language Models (LLMs) have shown that their reasoning ability could be enhanced through approaches like Chain-of-Thought (CoT) prompting. However, these methods use single prompts for different types of questions and do not design appropriate prompts for questions with different characteristics. In this paper, we aim to explore a methodology that generates differentially diverse reasoning paths for different types of questions. To achieve this, we propose a novel prompting strategy called Differential Diversity Prompting (DDPrompt). Firstly, we generate the optimal prompts collection based on question characteristics. Then, we use this optimal prompts collection to generate multiple answers for a question and choose the final answer by voting. We evaluated DDPrompt on twelve reasoning benchmarks and significant improvement in the performance of LLMs on complex reasoning tasks (e.g., GSM8K 75%->84%, Tracking Shuffled Objects (68.8%->83.9%))

Generalized zero-shot text classification aims to classify textual instances from both previously seen classes and incrementally emerging unseen classes. Most existing methods generalize poorly since the learned parameters are only optimal for seen classes rather than for both classes, and the parameters keep stationary in predicting procedures. To address these challenges, we propose a novel Learn to Adapt (LTA) network using a variant meta-learning framework. Specifically, LTA trains an adaptive classifier by using both seen and virtual unseen classes to simulate a generalized zero-shot learning (GZSL) scenario in accordance with the test time, and simultaneously learns to calibrate the class prototypes and sample representations to make the learned parameters adaptive to incoming unseen classes. We claim that the proposed model is capable of representing all prototypes and samples from both classes to a more consistent distribution in a global space. Extensive experiments on five text classification datasets show that our model outperforms several competitive previous approaches by large margins. The code and the whole datasets are available at https://github.com/Quareia/LTA.

The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks. These comprehensive benchmarks have facilitated a broad range of research and applications in natural language processing (NLP). The problem, however, is that most such benchmarks are limited to English, which has made it difficult to replicate many of the successes in English NLU for other languages. To help remedy this issue, we introduce the first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark. CLUE is an open-ended, community-driven project that brings together 9 tasks spanning several well-established single-sentence/sentence-pair classification tasks, as well as machine reading comprehension, all on original Chinese text. To establish results on these tasks, we report scores using an exhaustive set of current state-of-the-art pre-trained Chinese models (9 in total). We also introduce a number of supplementary datasets and additional tools to help facilitate further progress on Chinese NLU. Our benchmark is released at https://www.cluebenchmarks.com

This paper describes the IUCL system at VarDial 2019 evaluation campaign for the task of discriminating between Mainland and Taiwan variation of mandarin Chinese. We first build several base classifiers, including a Naive Bayes classifier with word n-gram as features, SVMs with both character and syntactic features, and neural networks with pre-trained character/word embeddings. Then we adopt ensemble methods to combine output from base classifiers to make final predictions. Our ensemble models achieve the highest F1 score (0.893) in simplified Chinese track and the second highest (0.901) in traditional Chinese track. Our results demonstrate the effectiveness and robustness of the ensemble methods.