RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL (2023 · 277 citations)
Seq2seq pre-trained models such as T5 and BART are a strong approach to Text-to-SQL. However, a single decoder must handle two jobs at once: picking the correct tables and columns (schema linking) and producing the SQL keyword structure (skeleton parsing). Queries with many schema items or complex operators make this…
CodeS: Towards Building Open-source Language Models for Text-to-SQL (2024 · 190 citations)
Most leading text-to-SQL systems rely on closed LLMs such as GPT-4 and ChatGPT. That brings opaque architectures, privacy concerns from sending data to API providers, and high inference costs. The authors address this with CodeS, a family of fully open-source models with 1B to 15B parameters. CodeS was made by…
AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation (2023 · 67 citations)
Multi-modal Large Language Models (MLLMs) often produce answers that sound plausible but do not match the image.
SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation (2024 · 21 citations)
SpreadsheetBench tackles a weakness in how LLM-based spreadsheet assistants are evaluated. Earlier benchmarks rely on synthetic or crowdsourced instructions, simple single-table sheets, and a single check per task. The authors collected solved questions from four Excel help forums (ExcelForum, Chandoo, MrExcel…
Dynamic Parallel Tree Search for Efficient LLM Reasoning (2025 · 13 citations)
Tree-of-Thoughts (ToT) style search, often driven by MCTS, improves LLM reasoning, but prior work has focused on accuracy rather than cost.
Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts (2026 · 4 citations)
Long reasoning rollouts in LLM reinforcement learning store large KV caches. This memory cost limits batch sizes and GPU utilization, especially since rollout generation takes most of the training time. The authors ask whether training-free KV compression, built for inference, can be used during rollouts. They find…
SDPA at BEA 2026 Shared Task 2: Efficient LLM Fine-Tuning for Rubric-based Short Answer Scoring (2026 · 1 citation)
The paper addresses automated short-answer scoring (ASA), where open-ended student answers must be graded against interrelated rubrics.
From Conversation to Evaluation: Benchmarking LLMs on Development Knowledge via SimpleDevQA (2026)
Developers often turn to LLMs for factual knowledge about tools, APIs and frameworks, but benchmarks for this Dev Knowledge QA task are narrow in the knowledge they cover and seldom rest on genuine user questions.
MTP-RL: Acceleration of Reinforcement Learning Rollouts with Policy-Aligned Multi-Token Prediction (2026)
Rollout generation consumes most of the compute in reinforcement-learning fine-tuning of LLMs, especially when models produce long reasoning chains.
Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation (2026)
Omni-I2C is a benchmark that tests whether Large Multimodal Models (LMMs) can turn structured digital graphics into executable code that reproduces the original image.

Co-authors here

12 of 48 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Cited by

Papers of our library cite their works 243 times (of the 149,439 papers whose bibliographies we read); 53 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jing-zhang/

🧑‍🔬 Jing Zhang

🏛️ Affiliations

🧭 Fields, topics and concepts

📅 Works by year

2020s

📄 Papers

🤝 Co-authors here

Venues

🔗 Cited by

Jing Zhang

Affiliations

Fields, topics and concepts

Works by year

Papers

Co-authors here

Cited by