107 citations · 122 across the 18 of their papers we have counts for
14 papers · 1 filter
Scaling Agentic Verifier for Competitive Coding
Zeyao Ma, Jing Zhang, Xiaokang Zhang +9
Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-base…
OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale
Haoyang Li, Shang Wu, Xiaokang Zhang +9
Text-to-SQL, the task of translating natural language questions into SQL queries, plays a crucial role in enabling non-experts to interact with databases. While recent advancements…
Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL
Hanbing Liu, Haoyang Li, Xiaokang Zhang +5
Direct Preference Optimization (DPO) has proven effective in complex reasoning tasks like math word problems and code generation. However, when applied to Text-to-SQL datasets, it…
Dynamic Scaling of Unit Tests for Code Reward Modeling
Zeyao Ma, Xiaokang Zhang, Jing Zhang +3
Current large language models (LLMs) often struggle to produce accurate responses on the first attempt for complex reasoning tasks like code generation. Prior research tackles this…
CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis
Bohan Zhang, Xiaokang Zhang, Jing Zhang +3
Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these method…
SAM Decoding: Speculative Decoding via Suffix Automaton
Yuxuan Hu, Ke Wang, Xiaokang Zhang +4
Speculative decoding (SD) has been demonstrated as an effective technique for lossless LLM inference acceleration. Retrieval-based SD methods, one kind of model-free method, have y…
SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
Zeyao Ma, Bohan Zhang, Jing Zhang +6
We introduce SpreadsheetBench, a challenging spreadsheet manipulation benchmark exclusively derived from real-world scenarios, designed to immerse current large language models (LL…
Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking
Xiaokang Zhang, Zijun Yao, Jing Zhang +4
Detecting non-factual content is a longstanding goal to increase the trustworthiness of large language models (LLMs) generations. Current factuality probes, trained using humananno…
Reverse That Number! Decoding Order Matters in Arithmetic Learning
Daniel Zhang-Li, Nianyi Lin, Jifan Yu +6
Recent advancements in pretraining have demonstrated that modern Large Language Models (LLMs) possess the capability to effectively learn arithmetic operations. However, despite ac…
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios
Xiaokang Zhang, Sijia Luo, Bohan Zhang +12
We introduce TableLLM, a robust large language model (LLM) with 8 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embe…
CodeS: Towards Building Open-source Language Models for Text-to-SQL
Haoyang Li, Jing Zhang, Hanbing Liu +7
Language models have shown promising performance on the task of translating natural language questions into SQL queries (Text-to-SQL). However, most of the state-of-the-art (SOTA)…
GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation
Jing Zhang, Xiaokang Zhang, Daniel Zhang-Li +10
We present GLM-Dialog, a large-scale language model (LLM) with 10B parameters capable of knowledge-grounded conversation in Chinese using a search engine to access the Internet kno…
Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
Jing Zhang, Xiaokang Zhang, Jifan Yu +4
Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning. A desired subgraph is crucial as a small one may exclude the answer but a large on…
Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models
Yu Feng, Jing Zhang, Xiaokang Zhang +3
Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constra…