大模型
arxiv.org ·
CHAI：通过 AI 反馈强化学习改进大语言模型的代码混合翻译
该论文针对 LLM 在代码混合（code-mixed）语言理解上的薄弱环节，提出通用框架 CHAI，聚焦代码混合翻译。方法包含四点：用 LLM 充当标注者以缓解高质量代码混合数据稀缺；基于这些标注生成大规模偏好数据并采用 RLAIF 优化翻译；引入 LLM 生成的领域知识作为 constitution 进行迭代式回答精修；在真实数据集与设置上做广泛评测。作者称 CHAI 增强后的 LLM 在代码混合翻译任务的人工裁决胜率上平均超过开源 SOTA 模型 68.45%，并称这是迈向更包容的开源代码混合 LLM 的一步。
AI推荐理由 arXiv 论文（v4，2026-09-12 修订），来源可信、摘要信息密度高。核心新信息是提出 CHAI 框架，用 LLM 作为标注者生成偏好数据，结合 RLAIF 与 LLM 生成的领域知识 constitution 迭代优化代码混合（code-mixed）翻译，并在真实数据集上报告人工裁决胜率平均超过开源 SOTA 68.45%。局限：该 68.45% 为作者自报的人工裁决胜率，摘要未给出数据集规模、基线清单与统计显著性，需查看全文验证；代码混合翻译属相对小众任务，对通用 Agent/应用落地的直接价值有限。
72
正文
Computer Science > Computation and Language
arXiv:2411.09073 (cs)
[Submitted on 13 Nov 2024 (v1), last revised 12 Sep 2026 (this version, v4)]
Title:CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback
Authors:Wenbo Zhang, Aditya Majumdar, Asif Ekbal, Amulya Yadav
View a PDF of the paper titled CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback, by Wenbo Zhang and 3 other authors
View PDF
HTML (experimental)
Abstract:Large language models (LLMs) show strong performance across many tasks but remain weak at understanding code-mixed (CM) language. Despite this limitation, improving LLMs for CM tasks has received little attention. To address this gap, we propose CHAI, a general-purpose framework for enhancing LLM performance on CM tasks, focusing on CM translation. CHAI leverages four key ideas. First, we investigate the use of LLMs as annotators to address the scarcity of high-quality CM datasets. Second, we leverage these LLM annotations to generate large-scale preference data and apply reinforcement learning from AI feedback (RLAIF) to improve CM translation. Third, we incorporate LLM-generated domain knowledge as a constitution, enabling iterative response refinement. Fourth, we perform extensive evaluations on real-world datasets and settings. Results show that CHAI-powered LLMs outperform state-of-the-art open-source models by 68.45% on average in human-adjudicated win rate on CM translation tasks. This work is a step toward more inclusive open-source code-mixed LLMs.
Comments:
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:
arXiv:2411.09073 [cs.CL]
(or
arXiv:2411.09073v4 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2411.09073
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Wenbo Zhang [view email]
[v1]
Wed, 13 Nov 2024 22:56:00 UTC (711 KB)
[v2]
Wed, 26 Feb 2025 20:11:35 UTC (625 KB)
[v3]
Wed, 9 Jul 2025 05:40:56 UTC (1,061 KB)
[v4]
Sat, 12 Sep 2026 20:04:23 UTC (3,661 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback, by Wenbo Zhang and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2024-11
Change to browse by:
cs
cs.AI
cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)