F.3 Sparse Reward with KL Penalty . . . . . . . . . . . . . . . . . . . . . . . . . . .

Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to improve the ROUGE score, which is the main evaluation metric for summarization, whereas controlling the summary length has not drawn much attention. In our work, we address a new problem of explicit character-level length control for summarization, and propose a dynamic programming algorithm based on the Connectionist Temporal Classification (CTC) model. Results show that our approach not only achieves higher ROUGE scores but also yields more complete sentences.

Recent advances in large language models (LLMs) have created new opportunities for symbolic music generation. However, existing formats such as MIDI, ABC, and MusicXML are either overly complex or structurally inconsistent, limiting their suitability for token-based learning architectures. To address these challenges, we propose HNote, a novel hexadecimal-based notation system extended from YNote, which encodes both pitch and duration within a fixed 32-unit measure framework. This design ensures alignment, reduces ambiguity, and is directly compatible with LLM architectures. We converted 12,300 Jiangnan-style songs generated from traditional folk pieces from YNote into HNote, and fine-tuned LLaMA-3.1(8B) using parameter-efficient LoRA. Experimental results show that HNote achieves a syntactic correctness rate of 82.5%, and BLEU and ROUGE evaluations demonstrate strong symbolic and structural similarity, producing stylistically coherent compositions. This study establishes HNote as an effective framework for integrating LLMs with cultural music modeling.

Role-playing Large language models (LLMs) are increasingly deployed in high-stakes domains such as healthcare, education, and governance, where failures can directly impact user trust and well-being. A cost effective paradigm for LLM role-playing is few-shot learning, but existing approaches often cause models to break character in unexpected and potentially harmful ways, especially when interacting with hostile users. Inspired by Retrieval-Augmented Generation (RAG), we reformulate LLM role-playing into a text retrieval problem and propose a new prompting framework called RAGs-to-Riches, which leverages curated reference demonstrations to condition LLM responses. We evaluate our framework with LLM-as-a-judge preference voting and introduce two novel token-level ROUGE metrics: Intersection over Output (IOO) to quantity how much an LLM improvises and Intersection over References (IOR) to measure few-shot demonstrations utilization rate during the evaluation tasks. When simulating interactions with a hostile user, our prompting strategy incorporates in its responses during inference an average of 35% more tokens from the reference demonstrations. As a result, across 453 role-playing interactions, our models are consistently judged as being more authentic, and remain in-character more often than zero-shot and in-context Learning (ICL) methods. Our method presents a scalable strategy for building robust, human-aligned LLM role-playing frameworks.

Large language models (LLMs) are known to memorize parts of their training data, raising important concerns around privacy and security. While previous research has focused on studying memorization in pre-trained models, much less is known about how knowledge distillation (KD) affects memorization.In this study, we explore how different KD methods influence the memorization of fine-tuned task data when a large teacher model is distilled into smaller student variants.This study demonstrates that distilling a larger teacher model, fine-tuned on a dataset, into a smaller variant not only lowers computational costs and model size but also significantly reduces the memorization risks compared to standard fine-tuning approaches.

Sentence summarization aims at compressing a long sentence into a short one that conveys the main idea of the input.

While large language models (LLMs) have demonstrated impressive performance across a wide range of natural language processing (NLP) tasks in high-resource languages, their capabilities in low-resource and minority languages remain significantly underexplored. Formosan languages -- a subgroup of Austronesian languages spoken in Taiwan -- are both linguistically rich and endangered, largely due to the sociolinguistic dominance of Mandarin. In this work, we introduce FORMOSANBENCH, the first benchmark for evaluating LLMs on low-resource Austronesian languages. It covers three endangered Formosan languages: Atayal, Amis, and Paiwan, across three core NLP tasks: machine translation, automatic speech recognition (ASR), and text summarization. We assess model performance in zero-shot, 10-shot, and fine-tuned settings using FORMOSANBENCH. Our results reveal a substantial performance gap between high-resource and Formosan languages. Existing LLMs consistently underperform across all tasks, with 10-shot learning and fine-tuning offering only limited improvements. These findings underscore the urgent need for more inclusive NLP technologies that can effectively support endangered and underrepresented languages. We release our datasets and code to facilitate future research in this direction.

Weaknesses: However, I have two major concerns: 1. As also mentioned by the authors, this paper is basically an expanded analysis of [3, 58]. Basically, the key techniques of classification-based reward and PPO have been explored in [58], and the major extension is that this paper uses a larger and better-engineered model, and adapts an online setting to the offline setting. Therefore, I feel this paper has very little novelty in the sense of machine learning. The authors are very honest about this in the Related Work (Line 86), though.

A question-answering (QA) system is to search suitable answers within a knowledge base. Current QA systems struggle with queries requiring complex reasoning or real-time knowledge integration. They are often supplemented with retrieval techniques on a data source such as Retrieval-Augmented Generation (RAG). However, RAG continues to face challenges in handling complex reasoning and logical connections between multiple sources of information. A novel approach for enhancing Large Language Models (LLMs) in knowledge-intensive QA tasks is presented through the automated generation of context-based QA pairs. This methodology leverages LLMs to create fine-tuning data, reducing reliance on human labelling and improving model comprehension and reasoning capabilities. The proposed system includes an automated QA generator and a model fine-tuner, evaluated using perplexity, ROUGE, BLEU, and BERTScore. Comprehensive experiments demonstrate improvements in logical coherence and factual accuracy, with implications for developing adaptable Artificial Intelligence (AI) systems. Mistral-7b-v0.3 outperforms Llama-3-8b with BERT F1, BLEU, and ROUGE scores 0.858, 0.172, and 0.260 of for the LLM generated QA pairs compared to scores of 0.836, 0.083, and 0.139 for the human annotated QA pairs.