Yen-Ting Lin

Chao-Han Huck Yang, Taejin Park, Yuan Gong et al. · gatech

Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model. To explore new capabilities in language modeling for speech processing, we introduce the generative speech transcription error correction (GenSEC) challenge. This challenge comprises three post-ASR language modeling tasks: (i) post-ASR transcription correction, (ii) speaker tagging, and (iii) emotion recognition. These tasks aim to emulate future LLM-based agents handling voice-based interfaces while remaining accessible to a broad audience by utilizing open pretrained language models or agent-based APIs. We also discuss insights from baseline evaluations, as well as lessons learned for designing future evaluations.

Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim et al.

This work focuses on in-context data augmentation for intent detection. Having found that augmentation via in-context prompting of large pre-trained language models (PLMs) alone does not improve performance, we introduce a novel approach based on PLMs and pointwise V-information (PVI), a metric that can measure the usefulness of a datapoint for training a model. Our method first fine-tunes a PLM on a small seed of training data and then synthesizes new datapoints - utterances that correspond to given intents. It then employs intent-aware filtering, based on PVI, to remove datapoints that are not helpful to the downstream intent classifier. Our method is thus able to leverage the expressive power of large language models to produce diverse training data. Empirical results demonstrate that our method can produce synthetic training data that achieve state-of-the-art performance on three challenging intent detection datasets under few-shot settings (1.28% absolute improvement in 5-shot and 1.18% absolute in 10-shot, on average) and perform on par with the state-of-the-art in full-shot settings (within 0.01% absolute, on average).

Yen-Ting Lin, Yun-Nung Chen

In the realm of language models, the nuanced linguistic and cultural intricacies of Traditional Chinese, as spoken in Taiwan, have been largely overlooked. This paper introduces Taiwan LLM, a pioneering Large Language Model that specifically caters to the Traditional Chinese language, with a focus on the variant used in Taiwan. Leveraging a comprehensive pretraining corpus and instruction-finetuning datasets, we have developed a model that not only understands the complexities of Traditional Chinese but also embodies the cultural context of Taiwan. Taiwan LLM represents the first of its kind, a model that is not only linguistically accurate but also culturally resonant with its user base. Our evaluations demonstrate that Taiwan LLM achieves superior performance in understanding and generating Traditional Chinese text, outperforming existing models that are predominantly trained on Simplified Chinese or English. The open-source release of Taiwan LLM invites collaboration and further innovation, ensuring that the linguistic diversity of Chinese speakers is embraced and well-served. The model, datasets, and further resources are made publicly available to foster ongoing research and development in this field.

Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim et al.

While rich, open-domain textual data are generally available and may include interesting phenomena (humor, sarcasm, empathy, etc.) most are designed for language processing tasks, and are usually in a non-conversational format. In this work, we take a step towards automatically generating conversational data using Generative Conversational Networks, aiming to benefit from the breadth of available language and knowledge data, and train open domain social conversational agents. We evaluate our approach on conversations with and without knowledge on the Topical Chat dataset using automatic metrics and human evaluators. Our results show that for conversations without knowledge grounding, GCN can generalize from the seed data, producing novel conversations that are less relevant but more engaging and for knowledge-grounded conversations, it can produce more knowledge-focused, fluent, and engaging conversations. Specifically, we show that for open-domain conversations with 10\% of seed data, our approach performs close to the baseline that uses 100% of the data, while for knowledge-grounded conversations, it achieves the same using only 1% of the data, on human ratings of engagingness, fluency, and relevance.

Ssu Chiu, Maolin Li, Yen-Ting Lin et al.

Dialogue systems are usually categorized into two types, open-domain and task-oriented. The first one focuses on chatting with users and making them engage in the conversations, where selecting a proper topic to fit the dialogue context is essential for a successful dialogue. The other one focuses on a specific task instead of casual talks, e.g., finding a movie on Friday night, or playing a song. These two directions have been studied separately due to their different purposes. However, how smoothly transitioning from social chatting to task-oriented dialogues is important for triggering business opportunities, and there is no public data focusing on such scenarios. Hence, this paper focuses on investigating the conversations starting from open-domain social chatting and then gradually transitioning to task-oriented purposes, and releases a large-scale dataset with detailed annotations for encouraging this research direction. To achieve this goal, this paper proposes a framework to automatically generate many dialogues without human involvement, in which any powerful open-domain dialogue generation model can be easily leveraged. The human evaluation shows that our generated dialogue data has a natural flow at a reasonable quality, showing that our released data has a great potential of guiding future research directions and commercial activities. Furthermore, the released models allow researchers to automatically generate unlimited dialogues in the target scenarios, which can greatly benefit semi-supervised and unsupervised approaches.

Hsin-Yu Chang, Pei-Yu Chen, Tun-Hsiang Chou et al.

This paper provides a detailed survey of synthetic data techniques. We first discuss the expected goals of using synthetic data in data augmentation, which can be divided into four parts: 1) Improving Diversity, 2) Data Balancing, 3) Addressing Domain Shift, and 4) Resolving Edge Cases. Synthesizing data are closely related to the prevailing machine learning techniques at the time, therefore, we summarize the domain of synthetic data techniques into four categories: 1) Expert-knowledge, 2) Direct Training, 3) Pre-train then Fine-tune, and 4) Foundation Models without Fine-tuning. Next, we categorize the goals of synthetic data filtering into four types for discussion: 1) Basic Quality, 2) Label Consistency, and 3) Data Distribution. In section 5 of this paper, we also discuss the future directions of synthetic data and state three direction that we believe is important: 1) focus more on quality, 2) the evaluation of synthetic data, and 3) multi-model data augmentation.

Jia-Jyu Su, Pang-Chen Liao, Yen-Ting Lin et al.

Services of personalized TTS systems for the Mandarin-speaking speech impaired are rarely mentioned. Taiwan started the VoiceBanking project in 2020, aiming to build a complete set of services to deliver personalized Mandarin TTS systems to amyotrophic lateral sclerosis patients. This paper reports the corpus design, corpus recording, data purging and correction for the corpus, and evaluations of the developed personalized TTS systems, for the VoiceBanking project. The developed corpus is named after the VoiceBank-2023 speech corpus because of its release year. The corpus contains 29.78 hours of utterances with prompts of short paragraphs and common phrases spoken by 111 native Mandarin speakers. The corpus is labeled with information about gender, degree of speech impairment, types of users, transcription, SNRs, and speaking rates. The VoiceBank-2023 is available by request for non-commercial use and welcomes all parties to join the VoiceBanking project to improve the services for the speech impaired.

Yen-Ting Lin, Hui-Chi Kuo, Ze-Song Xu et al.

This paper introduces Miutsu, National Taiwan University's Alexa Prize TaskBot, which is designed to assist users in completing tasks requiring multiple steps and decisions in two different domains -- home improvement and cooking. We overview our system design and architectural goals, and detail the proposed core elements, including question answering, task retrieval, social chatting, and various conversational modules. A dialogue flow is proposed to provide a robust and engaging conversation when handling complex tasks. We discuss the faced challenges during the competition and potential future work.

Sheng-Kai Chen, Jyh-Horng Wu, Ching-Yao Lin et al.

This paper presents an AI glasses system that integrates real-time voice processing, artificial intelligence(AI) agents, and cross-network streaming capabilities. The system employs dual-agent architecture where Agent 01 handles Automatic Speech Recognition (ASR) and Agent 02 manages AI processing through local Large Language Models (LLMs), Model Context Protocol (MCP) tools, and Retrieval-Augmented Generation (RAG). The system supports real-time RTSP streaming for voice and video data transmission, eye tracking data collection, and remote task execution through RabbitMQ messaging. Implementation demonstrates successful voice command processing with multilingual support and cross-platform task execution capabilities.

Yen-Ting Lin, Di Jin, Tengyu Xu et al.

Large language models (LLMs) have recently demonstrated remarkable success in mathematical reasoning. Despite progress in methods like chain-of-thought prompting and self-consistency sampling, these advances often focus on final correctness without ensuring that the underlying reasoning process is coherent and reliable. This paper introduces Step-KTO, a training framework that combines process-level and outcome-level binary feedback to guide LLMs toward more trustworthy reasoning trajectories. By providing binary evaluations for both the intermediate reasoning steps and the final answer, Step-KTO encourages the model to adhere to logical progressions rather than relying on superficial shortcuts. Our experiments on challenging mathematical benchmarks show that Step-KTO significantly improves both final answer accuracy and the quality of intermediate reasoning steps. For example, on the MATH-500 dataset, Step-KTO achieves a notable improvement in Pass@1 accuracy over strong baselines. These results highlight the promise of integrating stepwise process feedback into LLM training, paving the way toward more interpretable and dependable reasoning capabilities.

Yen-Ting Lin, Chao-Han Huck Yang, Zhehuai Chen et al.

Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and digesting their knowledge in a single model. Previous methods achieve this by having separate correction language models, resulting in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose a Multi-Task Correction MoE, where we train the experts to become an ``expert'' of speech-to-text, language-to-text and vision-to-text datasets by learning to route each dataset's tokens to its mapped expert. Experiments on the Open ASR Leaderboard show that we explore a new state-of-the-art performance by achieving an average relative $5.0$% WER reduction and substantial improvements in BLEU scores for speech and translation tasks. On zero-shot evaluation, NeKo outperforms GPT-3.5 and Claude-Opus with $15.5$% to $27.6$% relative WER reduction in the Hyporadise benchmark. NeKo performs competitively on grammar and post-OCR correction as a multi-task model.

Po-Heng Chen, Sijia Cheng, Wei-Lin Chen et al.

The evaluation of large language models (LLMs) has drawn substantial attention in the field recently. This work focuses on evaluating LLMs in a Chinese context, specifically, for Traditional Chinese which has been largely underrepresented in existing benchmarks. We present TMLU, a holistic evaluation suit tailored for assessing the advanced knowledge and reasoning capability in LLMs, under the context of Taiwanese Mandarin. TMLU consists of an array of 37 subjects across social science, STEM, humanities, Taiwan-specific content, and others, ranging from middle school to professional levels. In addition, we curate chain-of-thought-like few-shot explanations for each subject to facilitate the evaluation of complex reasoning skills. To establish a comprehensive baseline, we conduct extensive experiments and analysis on 24 advanced LLMs. The results suggest that Chinese open-weight models demonstrate inferior performance comparing to multilingual proprietary ones, and open-weight models tailored for Taiwanese Mandarin lag behind the Simplified-Chinese counterparts. The findings indicate great headrooms for improvement, and emphasize the goal of TMLU to foster the development of localized Taiwanese-Mandarin LLMs. We release the benchmark and evaluation scripts for the community to promote future research.

Ji-Lun Peng, Sijia Cheng, Egil Diau et al.

LLMs have gotten attention across various research domains due to their exceptional performance on a wide range of complex tasks. Therefore, refined methods to evaluate the capabilities of LLMs are needed to determine the tasks and responsibility they should undertake. Our study mainly discussed how LLMs, as useful tools, should be effectively assessed. We proposed the two-stage framework: from ``core ability'' to ``agent'', clearly explaining how LLMs can be applied based on their specific capabilities, along with the evaluation methods in each stage. Core ability refers to the capabilities that LLMs need in order to generate high-quality natural language texts. After confirming LLMs possess core ability, they can solve real-world and complex tasks as agent. In the "core ability" stage, we discussed the reasoning ability, societal impact, and domain knowledge of LLMs. In the ``agent'' stage, we demonstrated embodied action, planning, and tool learning of LLMs agent applications. Finally, we examined the challenges currently confronting the evaluation methods for LLMs, as well as the directions for future development.

Yen-Ting Lin, Yun-Nung Chen

We propose LLM-Eval, a unified multi-dimensional automatic evaluation method for open-domain conversations with large language models (LLMs). Existing evaluation methods often rely on human annotations, ground-truth responses, or multiple LLM prompts, which can be expensive and time-consuming. To address these issues, we design a single prompt-based evaluation method that leverages a unified evaluation schema to cover multiple dimensions of conversation quality in a single model call. We extensively evaluate the performance of LLM-Eval on various benchmark datasets, demonstrating its effectiveness, efficiency, and adaptability compared to state-of-the-art evaluation methods. Our analysis also highlights the importance of choosing suitable LLMs and decoding strategies for accurate evaluation results. LLM-Eval offers a versatile and robust solution for evaluating open-domain conversation systems, streamlining the evaluation process and providing consistent performance across diverse scenarios.

Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim et al.

Rich, open-domain textual data available on the web resulted in great advancements for language processing. However, while that data may be suitable for language processing tasks, they are mostly non-conversational, lacking many phenomena that appear in human interactions and this is one of the reasons why we still have many unsolved challenges in conversational AI. In this work, we attempt to address this by using Generative Conversational Networks to automatically generate data and train social conversational agents. We evaluate our approach on TopicalChat with automatic metrics and human evaluators, showing that with 10% of seed data it performs close to the baseline that uses 100% of the data.

Philipp Ennen, Yen-Ting Lin, Ali Girayhan Ozbay et al.

In a dialogue system pipeline, a natural language generation (NLG) unit converts the dialogue direction and content to a corresponding natural language realization. A recent trend for dialogue systems is to first pre-train on large datasets and then fine-tune in a supervised manner using datasets annotated with application-specific features. Though novel behaviours can be learned from custom annotation, the required effort severely bounds the quantity of the training set, and the application-specific nature limits the reuse. In light of the recent success of data-driven approaches, we propose the novel future bridging NLG (FBNLG) concept for dialogue systems and simulators. The critical step is for an FBNLG to accept a future user or system utterance to bridge the present context towards. Future bridging enables self supervised training over annotation-free datasets, decoupled the training of NLG from the rest of the system. An FBNLG, pre-trained with massive datasets, is expected to apply in classical or new dialogue scenarios with minimal adaptation effort. We evaluate a prototype FBNLG to show that future bridging can be a viable approach to a universal few-shot NLG for task-oriented and chit-chat dialogues.

Yen-Ting Lin, Yun-Nung Chen

There has been a rapid development in data-driven task-oriented dialogue systems with the benefit of large-scale datasets. However, the progress of dialogue systems in low-resource languages lags far behind due to the lack of high-quality data. To advance the cross-lingual technology in building dialog systems, DSTC9 introduces the task of cross-lingual dialog state tracking, where we test the DST module in a low-resource language given the rich-resource training dataset. This paper studies the transferability of a cross-lingual generative dialogue state tracking system using a multilingual pre-trained seq2seq model. We experiment under different settings, including joint-training or pre-training on cross-lingual and cross-ontology datasets. We also find out the low cross-lingual transferability of our approaches and provides investigation and discussion.

Pai-Yu Tan, Po-Yao Chuang, Yen-Ting Lin et al.

Neural network hardware is considered an essential part of future edge devices. In this paper, we propose a binary-weight spiking neural network (BW-SNN) hardware architecture for low-power real-time object classification on edge platforms. This design stores a full neural network on-chip, and hence requires no off-chip bandwidth. The proposed systolic array maximizes data reuse for a typical convolutional layer. A 5-layer convolutional BW-SNN hardware is implemented in 90nm CMOS. Compared with state-of-the-art designs, the area cost and energy per classification are reduced by 7$\times$ and 23$\times$, respectively, while also achieving a higher accuracy on the MNIST benchmark. This is also a pioneering SNN hardware architecture that supports advanced CNN architectures.