Related papers: Speech-Worthy Alignment for Japanese SpeechLLMs vi…
This paper presents a systematic methodology for building domain-specific Japanese small language models using QLoRA fine-tuning. We address three core questions: optimal training scale, base-model selection, and architecture-aware…
Spoken language models (SLMs) have emerged as a unified paradigm for speech understanding and generation, enabling natural human machine interaction. However, while most progress has focused on semantic accuracy and instruction following,…
Direct alignment algorithms have proven an effective step for aligning language models to human-desired behaviors. Current variants of the Direct Preference Optimization objective have focused on a strict setting where all tokens are…
While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming. Previous studies on automatic speech quality assessment address the problem by predicting human…
The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR). Prompting LLM with audio embeddings to generate transcriptions becomes the new state-of-the-art ASR. Despite LLMs being trained with an extensive…
A key requirement in developing Generative Language Models (GLMs) is to have their values aligned with human values. Preference-based alignment is a widely used paradigm for this purpose, in which preferences over generation pairs are first…
Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. Nevertheless, most of the previous work…
Recent multi-modal Large Language Models (LLMs) such as GPT-4o have demonstrated strong capabilities of direct speech interaction. However, the lack of specialized and comprehensive benchmarks for end-to-end speech LLM evaluation hinders…
Speech tokenization serves as the foundation of speech language model (LM), enabling them to perform various tasks such as spoken language modeling, text-to-speech, speech-to-text, etc. Most speech tokenizers are trained independently of…
Aligning pretrained language models (LMs) often requires large-scale preference data and substantial computational resources. These costs become even more prohibitive for multi-objective or pluralistic alignment. Is this truly necessary?…
We introduce JP-TL-Bench, a lightweight, open benchmark designed to guide the iterative development of Japanese-English translation systems. In this context, the challenge is often "which of these two good translations is better?" rather…
Estimating the log-likelihood of a given sentence under an autoregressive language model is straightforward: one can simply apply the chain rule and sum the log-likelihood values for each successive token. However, for masked language…
Using Japanese honorifics is challenging because it requires not only knowledge of the grammatical rules but also contextual information, such as social relationships. It remains unclear whether pre-trained large language models (LLMs) can…
Preference optimization techniques have become a standard final stage for training state-of-art large language models (LLMs). However, despite widespread adoption, the vast majority of work to-date has focused on first-class citizen…
While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information.…
Self-supervised learning (SSL) has been dramatically successful not only in monolingual but also in cross-lingual settings. However, since the two settings have been studied individually in general, there has been little research focusing…
Large language models (LLMs) are increasingly used in everyday communication, including multilingual interactions across different cultural contexts. While LLMs can now generate near-perfect literal translations, it remains unclear whether…
Prompt engineering relevance research has seen a notable surge in recent years, primarily driven by advancements in pre-trained language models and large language models. However, a critical issue has been identified within this domain: the…
Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…
Sentence-level (SL) machine translation (MT) has reached acceptable quality for many high-resourced languages, but not document-level (DL) MT, which is difficult to 1) train with little amount of DL data; and 2) evaluate, as the main…