Investigating Cost-Efficiency of LLM-Generated Training Data for Conversational Semantic Frame Analysis

Recent studies have demonstrated that few-shot learning allows LLMs to generate training data for supervised models at a low cost. However, the quality of LLM-generated data may not entirely match that of human-labeled data. This raises a crucial question: how should one balance the trade-off between the higher quality but more expensive human data and the lower quality yet substantially cheaper LLM-generated data? In this paper, we synthesized training data for conversational semantic frame analysis using GPT-4 and examined how to allocate budgets optimally to achieve the best performance. Our experiments, conducted across various budget levels, reveal that optimal cost-efficiency is achieved by combining both human and LLM-generated data across a wide range of budget levels. Notably, as the budget decreases, a higher proportion of LLM-generated data becomes more preferable.

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?

In this study, we investigate whether non-English-centric LLMs, despite their strong performance, `think' in their respective dominant language: more precisely, `think' refers to how the representations of intermediate layers, when un-embedded into the vocabulary space, exhibit higher probabilities for certain dominant languages during generation. We term such languages as internal $\textbf{latent languages}$. We examine the latent language of three typical categories of models for Japanese processing: Llama2, an English-centric model; Swallow, an English-centric model with continued pre-training in Japanese; and LLM-jp, a model pre-trained on balanced English and Japanese corpora. Our empirical findings reveal that, unlike Llama2 which relies exclusively on English as the internal latent language, Japanese-specific Swallow and LLM-jp employ both Japanese and English, exhibiting dual internal latent languages. For any given target language, the model preferentially activates the latent language most closely related to it. In addition, we explore how intermediate layers respond to questions involving cultural conflicts between latent internal and target output languages. We further explore how the language identity shifts across layers while keeping consistent semantic meaning reflected in the intermediate layer representations. This study deepens the understanding of non-English-centric large language models, highlighting the intricate dynamics of language representation within their intermediate layers.

Efficient Continual Learning with Low Memory Footprint For Edge Device

Continual learning(CL) is a useful technique to acquire dynamic knowledge continually. Although powerful cloud platforms can fully exert the ability of CL,e.g., customized recommendation systems, similar personalized requirements for edge devices are almost disregarded. This phenomenon stems from the huge resource overhead involved in training neural networks and overcoming the forgetting problem of CL. This paper focuses on these scenarios and proposes a compact algorithm called LightCL. Different from other CL methods bringing huge resource consumption to acquire generalizability among all tasks for delaying forgetting, LightCL compress the resource consumption of already generalized components in neural networks and uses a few extra resources to improve memory in other parts. We first propose two new metrics of learning plasticity and memory stability to seek generalizability during CL. Based on the discovery that lower and middle layers have more generalizability and deeper layers are opposite, we $\textit{Maintain Generalizability}$ by freezing the lower and middle layers. Then, we $\textit{Memorize Feature Patterns}$ to stabilize the feature extracting patterns of previous tasks to improve generalizability in deeper layers. In the experimental comparison, LightCL outperforms other SOTA methods in delaying forgetting and reduces at most $\textbf{6.16$\times$}$ memory footprint, proving the excellent performance of LightCL in efficiency. We also evaluate the efficiency of our method on an edge device, the Jetson Nano, which further proves our method's practical effectiveness.

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs). LLM-jp aims to develop open-source and strong Japanese LLMs, and as of this writing, more than 1,500 participants from academia and industry are working together for this purpose. This paper presents the background of the establishment of LLM-jp, summaries of its activities, and technical reports on the LLMs developed by LLM-jp. For the latest activities, visit https://llm-jp.nii.ac.jp/en/.

Enhancing In-Context Learning with Semantic Representations for Relation Extraction

In this work, we employ two AMR-enhanced semantic representations for ICL on RE: one that explores the AMR structure generated for a sentence at the subgraph level (shortest AMR path), and another that explores the full AMR structure generated for a sentence. In both cases, we demonstrate that all settings benefit from the fine-grained AMR's semantic structure. We evaluate our model on four RE datasets. Our results show that our model can outperform the GPT-based baselines, and achieve SOTA performance on two of the datasets, and competitive performance on the other two.

Generalized W-Net: Arbitrary-style Chinese Character Synthesization

Synthesizing Chinese characters with consistent style using few stylized examples is challenging. Existing models struggle to generate arbitrary style characters with limited examples. In this paper, we propose the Generalized W-Net, a novel class of W-shaped architectures that addresses this. By incorporating Adaptive Instance Normalization and introducing multi-content, our approach can synthesize Chinese characters in any desired style, even with limited examples. It handles seen and unseen styles during training and can generate new character contents. Experimental results demonstrate the effectiveness of our approach.

Jump-teaching: Ultra Efficient and Robust Learning with Noisy Label

Sample selection is the most straightforward technique to combat label noise, aiming to distinguish mislabeled samples during training and avoid the degradation of the robustness of the model. In the workflow, $\textit{selecting possibly clean data}$ and $\textit{model update}$ are iterative. However, their interplay and intrinsic characteristics hinder the robustness and efficiency of learning with noisy labels: 1) The model chooses clean data with selection bias, leading to the accumulated error in the model update. 2) Most selection strategies leverage partner networks or supplementary information to mitigate label corruption, albeit with increased computation resources and lower throughput speed. Therefore, we employ only one network with the jump manner update to decouple the interplay and mine more semantic information from the loss for a more precise selection. Specifically, the selection of clean data for each model update is based on one of the prior models, excluding the last iteration. The strategy of model update exhibits a jump behavior in the form. Moreover, we map the outputs of the network and labels into the same semantic feature space, respectively. In this space, a detailed and simple loss distribution is generated to distinguish clean samples more effectively. Our proposed approach achieves almost up to $2.53\times$ speedup, $0.46\times$ peak memory footprint, and superior robustness over state-of-the-art works with various noise settings.

AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA

We propose a voting-driven semi-supervised approach to automatically acquire the typical duration of an event and use it as pseudo-labeled data. The human evaluation demonstrates that our pseudo labels exhibit surprisingly high accuracy and balanced coverage. In the temporal commonsense QA task, experimental results show that using only pseudo examples of 400 events, we achieve performance comparable to the existing BERT-based weakly supervised approaches that require a significant amount of training examples. When compared to the RoBERTa baselines, our best approach establishes state-of-the-art performance with a 7% improvement in Exact Match.

Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese

The creation of instruction data and evaluation benchmarks for serving Large language models often involves enormous human annotation. This issue becomes particularly pronounced when rapidly developing such resources for a non-English language like Japanese. Instead of following the popular practice of directly translating existing English resources into Japanese (e.g., Japanese-Alpaca), we propose an efficient self-instruct method based on GPT-4. We first translate a small amount of English instructions into Japanese and post-edit them to obtain native-level quality. GPT-4 then utilizes them as demonstrations to automatically generate Japanese instruction data. We also construct an evaluation benchmark containing 80 questions across 8 categories, using GPT-4 to automatically assess the response quality of LLMs without human references. The empirical results suggest that the models fine-tuned on our GPT-4 self-instruct data significantly outperformed the Japanese-Alpaca across all three base pre-trained models. Our GPT-4 self-instruct data allowed the LLaMA 13B model to defeat GPT-3.5 (Davinci-003) with a 54.37\% win-rate. The human evaluation exhibits the consistency between GPT-4's assessments and human preference. Our high-quality instruction data and evaluation benchmark have been released here.

Ethical implications of ChatGPT in higher education: A scoping review

This scoping review explores the ethical challenges of using ChatGPT in education, focusing particularly on issues related to higher education. By reviewing recent academic articles written in English, Chinese, and Japanese, we aimed to provide a comprehensive overview of relevant research while identifying gaps for future considerations. Drawing on Arksey and O'Malley's (2005) five-stage scoping review framework, we identified research questions, search terms, and conducted article search from four databases in the target three languages. Each article was reviewed by at least two researchers identifying the main ethical issues of utilizing AI in education, particularly higher education. Our analysis of ethical issues followed the framework developed by DeepMind (Weiginger et al., 2021) to identify six main areas of ethical concern in Language Models. The majority of papers were concerned with misinformation harms (n=25) and/or human-computer interaction related harms (n=24). Given the rapid deployment of Generative Artificial Intelligence (GAI), it is imperative for educators to conduct more empirical studies to develop sound ethical policies for the use of GAI.