English
Related papers

Related papers: Self-Alignment with Instruction Backtranslation

200 papers

Using in-context learning (ICL) for data generation, techniques such as Self-Instruct (Wang et al., 2023) or the follow-up Alpaca (Taori et al., 2023) can train strong conversational agents with only a small amount of human supervision. One…

Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving…

Computation and Language · Computer Science 2024-06-11 Ming Li , Lichang Chen , Jiuhai Chen , Shwai He , Jiuxiang Gu , Tianyi Zhou

Large language models (LLMs) struggle to follow instructions with complex constraints in format, length, etc. Following the conventional instruction-tuning practice, previous works conduct post-training on complex instruction-response pairs…

Computation and Language · Computer Science 2025-04-30 Yunjia Qi , Hao Peng , Xiaozhi Wang , Bin Xu , Lei Hou , Juanzi Li

Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning. The fine-tuning data is generally sequentially concatenated from a specific…

Computation and Language · Computer Science 2023-08-24 Yijin Liu , Xianfeng Zeng , Fandong Meng , Jie Zhou

Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically…

Computation and Language · Computer Science 2024-02-01 Pinzhen Chen , Shaoxiong Ji , Nikolay Bogoychev , Andrey Kutuzov , Barry Haddow , Kenneth Heafield

Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a…

Computation and Language · Computer Science 2024-12-17 Yutong Wu , Di Huang , Wenxuan Shi , Wei Wang , Lingzhe Gao , Shihao Liu , Ziyuan Nan , Kaizhao Yuan , Rui Zhang , Xishan Zhang , Zidong Du , Qi Guo , Yewen Pu , Dawei Yin , Xing Hu , Yunji Chen

The improvement of LLMs' instruction-following capabilities relies heavily on the availability of high-quality instruction-response pairs. Unfortunately, the current methods used to collect the pairs suffer from either unaffordable labor…

Computation and Language · Computer Science 2024-05-28 Yongrui Chen , Haiyun Jiang , Xinting Huang , Shuming Shi , Guilin Qi

Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies…

Computation and Language · Computer Science 2024-10-04 Xiao Yu , Qingyang Wu , Yu Li , Zhou Yu

Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning. Unfortunately, the performance of LLMs is greatly influenced by the quality of…

Computation and Language · Computer Science 2023-10-23 Zhihan Zhang , Shuohang Wang , Wenhao Yu , Yichong Xu , Dan Iter , Qingkai Zeng , Yang Liu , Chenguang Zhu , Meng Jiang

We propose iteratively prompting a large language model to self-correct a translation, with inspiration from their strong language understanding and translation capability as well as a human-like translation approach. Interestingly,…

Computation and Language · Computer Science 2024-05-03 Pinzhen Chen , Zhicheng Guo , Barry Haddow , Kenneth Heafield

Human preference alignment can greatly enhance Multimodal Large Language Models (MLLMs), but collecting high-quality preference data is costly. A promising solution is the self-evolution strategy, where models are iteratively trained on…

Machine Learning · Computer Science 2024-12-23 Wentao Tan , Qiong Cao , Yibing Zhan , Chao Xue , Changxing Ding

Instruction tuning of open-source large language models (LLMs) like LLaMA, using direct outputs from more powerful LLMs such as Instruct-GPT and GPT-4, has proven to be a cost-effective way to align model behaviors with human preferences.…

Computation and Language · Computer Science 2023-10-23 Haoran Li , Yiran Liu , Xingxing Zhang , Wei Lu , Furu Wei

Existing large language models show disparate capability across different languages, due to the imbalance in the training data. Their performances on English tasks are often stronger than on tasks of other languages. In this paper, we…

Computation and Language · Computer Science 2023-10-10 Wenhao Zhu , Yunzhe Lv , Qingxiu Dong , Fei Yuan , Jingjing Xu , Shujian Huang , Lingpeng Kong , Jiajun Chen , Lei Li

Instruction tuning is a supervised fine-tuning approach that significantly improves the ability of large language models (LLMs) to follow human instructions. We propose SelfCodeAlign, the first fully transparent and permissive pipeline for…

Computation and Language · Computer Science 2024-11-04 Yuxiang Wei , Federico Cassano , Jiawei Liu , Yifeng Ding , Naman Jain , Zachary Mueller , Harm de Vries , Leandro von Werra , Arjun Guha , Lingming Zhang

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially…

Computation and Language · Computer Science 2019-11-28 Ateret Anaby-Tavor , Boaz Carmeli , Esther Goldbraich , Amir Kantor , George Kour , Segev Shlomov , Naama Tepper , Naama Zwerdling

Autoformalization, the process of transforming informal mathematical language into formal specifications and proofs remains a difficult task for state-of-the-art (large) language models. Existing works point to competing explanations for…

Artificial Intelligence · Computer Science 2025-02-25 Willy Chan , Michael Souliman , Jakob Nordhagen , Brando Miranda , Elyas Obbad , Kai Fronsdal Sanmi Koyejo

This paper describes an alignment-based model for interpreting natural language instructions in context. We approach instruction following as a search over plans, scoring sequences of actions conditioned on structured observations of text…

Computation and Language · Computer Science 2017-04-14 Jacob Andreas , Dan Klein

Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an…

Computation and Language · Computer Science 2024-06-19 Shimao Zhang , Changjiang Gao , Wenhao Zhu , Jiajun Chen , Xin Huang , Xue Han , Junlan Feng , Chao Deng , Shujian Huang

Large language models (LLMs) often demonstrate inconsistencies with human preferences. Previous research typically gathered human preference data and then aligned the pre-trained models using reinforcement learning or instruction tuning,…

Computation and Language · Computer Science 2023-10-10 Yuhui Li , Fangyun Wei , Jinjing Zhao , Chao Zhang , Hongyang Zhang

The quality of finetuning data is crucial for aligning large language models (LLMs) with human values. Current methods to improve data quality are either labor-intensive or prone to factual errors caused by LLM hallucinations. This paper…

Computation and Language · Computer Science 2024-04-18 Run-Ze Fan , Xuefeng Li , Haoyang Zou , Junlong Li , Shwai He , Ethan Chern , Jiewen Hu , Pengfei Liu