31 citations · 67 across the 26 of their papers we have counts for
27 papers
Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation
Zeli Su, Ziyin Zhang, Zewei Pan +8
Low-resource target-language generation is often limited by scarce parallel data, while high-resource source-language monolingual data is abundant but difficult to use with standar…
FTibSuite: A Comprehensive Resource Suite for Tibetan Vision-Language Modeling
Guixian Xu, Yide Liang, Zeli Su +5
Vision-language models have progressed rapidly, but Tibetan remains a severely underserved low-resource language due to the lack of reproducible training and evaluation infrastruct…
TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale
Jun Wang, Ziyin Zhang, Rui Wang +2
Real-time detection and mitigation of technical anomalies are critical for large-scale cloud-native services, where even minutes of downtime can result in massive financial losses…
ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World
Ziyin Zhang, Zihan Liao, Hang Yu +2
The development of high-quality text embeddings is increasingly drifting toward an exclusionary future, defined by three critical barriers: prohibitive computational costs, a narro…
Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax
Zeli Su, Ziyin Zhang, Zhou Liu +7
Extending large language models (LLMs) to low-resource languages often incurs an "alignment tax": improvements in the target language come at the cost of catastrophic forgetting in…
Beyond Retrieval: A Multitask Benchmark and Model for Code Search
Siqiao Xue, Zihan Liao, Jin Qin +4
Code search has usually been evaluated as first-stage retrieval, even though production systems rely on broader pipelines with reranking and developer-style queries. Existing bench…
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Ziyin Zhang, Zihan Liao, Hang Yu +2
We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million…
C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling
Jin Qin, Zihan Liao, Ziyin Zhang +3
We present C2LLM - Contrastive Code Large Language Models, a family of code embedding models in both 0.5B and 7B sizes. Building upon Qwen-2.5-Coder backbones, C2LLM adopts a Pooli…
SHRP: Specialized Head Routing and Pruning for Efficient Encoder Compression
Zeli Su, Ziyin Zhang, Wenzheng Zhang +3
Transformer encoders are widely deployed in large-scale web services for natural language understanding tasks such as text classification, semantic retrieval, and content ranking.…
CodeFuse-CR-Bench: A Comprehensiveness-aware Benchmark for End-to-End Code Review Evaluation in Python Projects
Hanyang Guo, Xunjin Zheng, Zihan Liao +4
Automated code review (CR) is a key application for Large Language Models (LLMs), but progress is hampered by a "reality gap": existing benchmarks evaluate models on isolated sub-t…
BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data
Jaap Jumelet, Abdellah Fourtassi, Akari Haga +23
We present BabyBabelLM, a multilingual collection of datasets modeling the language a person observes from birth until they acquire a native language. We curate developmentally pla…
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Ziyin Zhang, Zihan Liao, Hang Yu +2
We introduce F2LLM - Foundation to Feature Large Language Models, a suite of state-of-the-art embedding models in three sizes: 0.6B, 1.7B, and 4B. Unlike previous top-ranking embed…
CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China
Guixian Xu, Zeli Su, Ziyin Zhang +4
Minority languages in China, such as Tibetan, Uyghur, and Traditional Mongolian, face significant challenges due to their unique writing systems, which differ from international st…
From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms
Zhaokun Jiang, Ziyin Zhang
Recent advancements in machine learning have spurred growing interests in automated interpreting quality assessment. Nevertheless, existing research suffers from insufficient exami…
Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
Hongyuan Tao, Ying Zhang, Zhenhao Tang +12
Recent advances in Large Language Models (LLMs) have shown promise in function-level code generation, yet repository-level software engineering tasks remain challenging. Current so…
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
Ziyin Zhang, Jiahao Xu, Zhiwei He +10
Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approache…
Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages
Zeli Su, Ziyin Zhang, Guixian Xu +4
While multilingual language models like XLM-R have advanced multilingualism in NLP, they still perform poorly in extremely low-resource languages. This situation is exacerbated by…
Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation
Ziyin Zhang, Jiahao Xu, Tian Liang +4
Conventional speculative decoding (SD) methods utilize a predefined length policy for proposing drafts, which implies the premise that the target model smoothly accepts the propose…
GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding
Ziyin Zhang, Hang Yu, Shijie Li +3
Programming languages possess rich semantic information - such as data flow - that is represented by graphs and not available from the surface form of source code. Recent code lang…
Multiple-Choice Questions are Efficient and Robust LLM Evaluators
Ziyin Zhang, Zhaokun Jiang, Lizhen Xu +2
We present GSM-MC, a multiple-choice (MC) dataset constructed by collecting answers and incorrect predictions on GSM8K from 60 open-source models. Through extensive experiments, we…
Is Self-knowledge and Action Consistent or Not: Investigating Large Language Model's Personality
Yiming Ai, Zhiwei He, Ziyin Zhang +5
In this study, we delve into the validity of conventional personality questionnaires in capturing the human-like personality traits of Large Language Models (LLMs). Our objective i…
Convergences and Divergences between Automatic Assessment and Human Evaluation: Insights from Comparing ChatGPT-Generated Translation and Neural Machine Translation
Zhaokun Jiang, Qianxi Lv, Ziyin Zhang +1
Large language models have demonstrated parallel and even superior translation performance compared to neural machine translation (NMT) systems. However, existing comparative studi…
Distinguishing Translations by Human, NMT, and ChatGPT: A Linguistic and Statistical Approach
Zhaokun Jiang, Qianxi Lv, Ziyin Zhang +1
The growing popularity of neural machine translation (NMT) and LLMs represented by ChatGPT underscores the need for a deeper understanding of their distinct characteristics and rel…
MELA: Multilingual Evaluation of Linguistic Acceptability
Ziyin Zhang, Yikang Liu, Weifang Huang +3
In this work, we present the largest benchmark to date on linguistic acceptability: Multilingual Evaluation of Linguistic Acceptability -- MELA, with 46K samples covering 10 langua…