By training on text in various languages, large language models (LLMs) typically possess multilingual support and demonstrate remarkable capabilities in solving tasks described in different languages. However, LLMs can exhibit linguistic discrimination due to the uneven distribution of training data across languages. That is, LLMs are hard to keep the consistency of responses when faced with the same task but depicted in different languages.
In this study, we first explore the consistency in the LLMs' outputs responding to queries in various languages from two aspects: safety and quality. We conduct this analysis with two datasets (AdvBench and NQ) based on four LLMs (Llama2-13b, Gemma-7b, GPT-3.5-turbo and Gemini-pro). The results show that LLMs exhibit stronger human alignment capabilities with queries in English, French, Russian, and Spanish (only 1.04\% of harmful queries successfully jailbreak on average) compared to queries in Bengali, Georgian, Nepali and Maithili (27.7\% of harmful queries jailbreak successfully on average). Moreover, for queries in English, Danish, Czech and Slovenian, LLMs tend to produce responses with a higher quality (with 0.1494 $F_1$ score on average) compared to the other languages. Upon these findings, we propose LDFighter, a similarity-based voting, to mitigate the linguistic discrimination in LLMs. LDFighter ensures consistent service for different language speakers. We evaluate LDFighter with both benign queries and harmful queries. The results show that LDFighter not only significantly reduces the jailbreak success rate but also improve the response quality on average, demonstrating its effectiveness.
BRIDGE the Gap: Mitigating Bias Amplification in Automated Scoring of English Language Learners via Inter-group Data Augmentation
School of Computing, University of Georgia, Athens, GA, USA（佐治亚大学计算机学院，美国亚特兰大，GA）；Educational Testing Service, Princeton, NJ, USA（教育测试服务，美国新泽西州普林斯顿，NJ）；AI4STEM Education Center, University of Georgia, Athens, GA, USA（AI4STEM教育中心，佐治亚大学，美国亚特兰大，GA）；The Hong Kong Polytechnic University, Hong Kong, China（香港理工大学，中国香港）
Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Johns Hopkins University（约翰霍普金斯大学）；Michigan State University（密歇根州立大学）；University of Mississippi（密苏里州立大学）
Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）科学与工程学院）；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）人工智能学院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society, China（深圳人工智能与机器人研究院）
Concurrent Linguistic Error Detection (CLED): a New Methodology for Error Detection in Large Language Models
Tianjin University of Technology（天津理工大学）；Tianjin University（天津大学）；University of Electronic Science and Technology of China（电子科技大学）；Northeastern University（东北大学）
VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China（复旦大学计算机科学与人工智能学院，上海，中国）；Shanghai Key Laboratory of Intelligent Information Processing（上海智能信息处理重点实验室）
Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
Xi’an Jiaotong University（西安交通大学）；National Engineering Laboratory for Big Data Analytics（国家大数据分析工程实验室）；Nanyang Technological University（南洋理工大学）；Lenovo Research（联想研究院）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）；Zhejiang University of Technology（浙江工业大学）
Mitigating the Linguistic Gap with Phonemic Representations for Robust Cross-lingual Transfer
Korea University（高丽大学）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；Sogang University（西江大学）；GIST（光州科学技术院）；Yonsei University（延世大学）；Carnegie Mellon University（卡内基梅隆大学）
taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades
Faculty for Computer Science and Mathematics, Hochschule München University of Applied Sciences（计算机科学与数学系，慕尼黑应用科学大学）；Department of Statistics, LMU Munich（统计学系，慕尼黑大学）；Munich Center for Machine Learning (MCML), LMU Munich（慕尼黑机器学习中心（MCML），慕尼黑大学）
Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corpora
Faculty for Computer Science and Mathematics, Hochschule München University of Applied Sciences（慕尼黑应用科学大学计算机科学与数学学院）；Department of Statistics, LMU Munich（慕尼黑大学统计学系）；Munich Center for Machine Learning (MCML), LMU Munich（慕尼黑大学机器学习中心）
Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective
School of Computer Science & Technology, NLP Lab, Soochow University, China（计算机科学与技术学院、自然语言处理实验室、苏州大学）；Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University（中文与双语研究系、香港理工大学）
