English
Related papers

Related papers: Self-Alignment with Instruction Backtranslation

200 papers

Although large language models (LLMs) have achieved remarkable performance across various tasks, they remain prone to errors. A key challenge is enabling them to self-correct. While prior research has relied on external tools or large…

Computation and Language · Computer Science 2025-03-12 Viktor Moskvoretskii , Chris Biemann , Irina Nikishina

Large-scale high-quality training data is important for improving the performance of models. After trained with data that has rationales (reasoning steps), models gain reasoning capability. However, the dataset with high-quality rationales…

Computation and Language · Computer Science 2024-05-01 Yunlong Feng , Yang Xu , Libo Qin , Yasheng Wang , Wanxiang Che

Alignment with human preference is a desired property of large language models (LLMs). Currently, the main alignment approach is based on reinforcement learning from human feedback (RLHF). Despite the effectiveness of RLHF, it is intricate…

Computation and Language · Computer Science 2024-04-16 Geyang Guo , Ranchi Zhao , Tianyi Tang , Wayne Xin Zhao , Ji-Rong Wen

The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention. However, employing LLMs for large-scale inference or domain-specific fine-tuning requires immense…

Computation and Language · Computer Science 2024-04-16 Ruohong Zhang , Yau-Shian Wang , Yiming Yang

Fine-tuning large pre-trained language models with Evol-Instruct has achieved encouraging results across a wide range of tasks. However, designing effective evolving methods for instruction evolution requires substantial human expertise.…

Computation and Language · Computer Science 2024-06-04 Weihao Zeng , Can Xu , Yingxiu Zhao , Jian-Guang Lou , Weizhu Chen

The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task.…

Computation and Language · Computer Science 2021-09-14 Zewen Chi , Li Dong , Bo Zheng , Shaohan Huang , Xian-Ling Mao , Heyan Huang , Furu Wei

Enhancing the instruction-following ability of Large Language Models (LLMs) primarily demands substantial instruction-tuning datasets. However, the sheer volume of these imposes a considerable computational burden and annotation cost. To…

Computation and Language · Computer Science 2023-11-15 Shengguang Wu , Keming Lu , Benfeng Xu , Junyang Lin , Qi Su , Chang Zhou

Annotated data has become the most important bottleneck in training accurate machine learning models, especially for areas that require domain expertise. A recent approach to deal with the above issue proposes using natural language…

Computation and Language · Computer Science 2021-01-19 Yannis Papanikolaou

Even though large language models (LLMs) have demonstrated remarkable capability in solving various natural language tasks, the capability of an LLM to follow human instructions is still a concern. Recent works have shown great improvements…

Computation and Language · Computer Science 2024-03-05 Xinbo Wu , Lav R. Varshney

Instruction tuning is widely used to improve a pre-trained Multimodal Large Language Model (MLLM) by training it on curated task-specific datasets, enabling better comprehension of human instructions. However, it is infeasible to collect…

Computation and Language · Computer Science 2025-05-30 Haiyang Guo , Fanhu Zeng , Ziwei Xiang , Fei Zhu , Da-Han Wang , Xu-Yao Zhang , Cheng-Lin Liu

Recent instruction-finetuned large language models (LMs) have achieved notable performances in various tasks, such as question-answering (QA). However, despite their ability to memorize a vast amount of general knowledge across diverse…

Computation and Language · Computer Science 2023-10-23 Soyeong Jeong , Jinheon Baek , Sukmin Cho , Sung Ju Hwang , Jong C. Park

Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of…

In this paper, we propose an effective way for biasing the attention mechanism of a sequence-to-sequence neural machine translation (NMT) model towards the well-studied statistical word alignment models. We show that our novel guided…

Computation and Language · Computer Science 2016-07-07 Wenhu Chen , Evgeny Matusov , Shahram Khadivi , Jan-Thorsten Peter

Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic…

Computation and Language · Computer Science 2023-08-31 Liangming Pan , Michael Saxon , Wenda Xu , Deepak Nathani , Xinyi Wang , William Yang Wang

Large language models encode impressively broad world knowledge in their parameters. However, the knowledge in static language models falls out of date, limiting the model's effective "shelf life." While online fine-tuning can reduce this…

Computation and Language · Computer Science 2023-10-24 Nathan Hu , Eric Mitchell , Christopher D. Manning , Chelsea Finn

Large Language Models have become the de facto approach to sequence-to-sequence text generation tasks, but for specialized tasks/domains, a pretrained LLM lacks specific capabilities to produce accurate or well-formatted responses.…

Computation and Language · Computer Science 2024-03-20 Jiuhai Chen , Jonas Mueller

Fine-tuning Large Language Models (LLMs) incurs considerable training costs, driving the need for data-efficient training with optimised data ordering. Human-inspired strategies offer a solution by organising data based on human learning…

Computation and Language · Computer Science 2024-11-06 Yushi Yang , Andrew M. Bean , Robert McCraith , Adam Mahdi

While alignment of texts on the sentential level is often seen as being too coarse, and word alignment as being too fine-grained, bi- or multilingual texts which are aligned on a level in-between are a useful resource for many purposes.…

Computation and Language · Computer Science 2007-05-23 Lea Cyrus , Hendrik Feddes

The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al., 2023). Here we consider the impact on…

Computation and Language · Computer Science 2024-10-04 Constanza Fierro , Jiaang Li , Anders Søgaard

Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback (RLHF) to align the output of large language models (LLMs) with human…

Machine Learning · Computer Science 2023-12-05 Zhiqing Sun , Yikang Shen , Qinhong Zhou , Hongxin Zhang , Zhenfang Chen , David Cox , Yiming Yang , Chuang Gan