Papers by Kun Hu

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis (2025.emnlp-main)

Challenge:	Autoregressive (AR) and diffusion language models (DLMs) suffer from insufficient reasoning capabilities.
Approach:	They propose a fully connected Diffusion Language Model that uses a concept-level causal graph to guide attention to learn causal relationships between concepts.
Outcome:	The proposed model achieves a 12% improvement and 3.2 training speedup on the COT-OrderPerturb task, along with an average gain of 1.31% across six downstream reasoning tasks.

Copied to clipboard

Haoming Huang, Yibo Yan, Jiahao Huo, Xin Zou, Xinfeng Li, Kun Wang, Xuming Hu

Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models (2026.acl-long)

Challenge:	Large Language Models (LLMs) are hampered by hallucinations, a particularly challenging variant, knowledge overshadowing, which can lead to erroneous outputs even with high-quality training data.
Approach:	They propose a framework to analyze and detect knowledge overshadowing by using knowledge circuit analysis to dissect the function of key components in the circuit and how attention pattern dynamics contribute to the phenomenon.
Outcome:	Extensive experiments show that the framework can detect and analyze knowledge overshadowing and improves on existing models.

Copied to clipboard

Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, Haojian Jin, Zhiting Hu

DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing (2026.findings-acl)

Challenge:	closed-ended question-based benchmarks struggle with saturation as newer models emerge . crowd-sourced leaderboards rely on costly and slow human judges .
Approach:	They propose a framework that leverages collective intelligence from all large language models to evaluate each other.
Outcome:	a new framework enables a democratic, pairwise evaluation of all large language models . it achieves 97% correlation with human judgements, while significantly reducing the cost.

Copied to clipboard

Hongzhi Zhang, Yuanze Hu, Tinghai Zhang, Jia Fu, Tao Wang, Junwei Jing, Zhaoxin Fan, Wei Bi, Ruiming Tang, Han Li, Guorui Zhou, Kun Gai

Information Retrieval

Challenge:	Large Language Models (LLMs) are evolving towards autonomous agents . retrieval capabilities are well-benchmarked, but post-retrieval synthesis is under-evaluated due to open-ended writing.
Approach:	They propose a benchmark to evaluate information consolidation capabilities using survey papers as gold standards.
Outcome:	The proposed benchmark analyzes the post-retrieval synthesis stage of large language models . it leverages high-quality survey papers as gold standards and reverse-engineers research requests . the proposed benchmark outperforms single-turn generation and reduces hallucinations .

Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents (2026.acl-long)

Copied to clipboard

Yiting Shen, Kun Li, Wei Zhou, Songlin Hu

Challenge:	Existing benchmarks focus on direct queries for a factual answer, but fail to evaluate the more crucial capability of actively applying memory to execute tasks.
Approach:	They propose a benchmark to evaluate whether agents can proactively leverage long-term memory to execute tool-based actions by selecting appropriate tools and grounding their parameters.
Outcome:	The proposed benchmarks show that 91.3% of tasks are memory-dependent . the benchmarks simulate persistent assistant usage, where users mention the same topic across long, interrupted interactions and expect previously established preferences and task states to be implicitly applied.

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen

FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging (2025.acl-long)

Challenge:	Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection.
Approach:	They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization.
Outcome:	The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models.

Copied to clipboard

Zichen Tang, Haihong E, Ziyan Ma, Haoyang He, Jiacheng Liu, Zhongjun Yang, Zihua Rong, Rongjin Li, Kun Ji, Qing Huang, Xinyang Hu, Yang Liu, Qianhe Zheng

DATA-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning (2024.findings-acl)

Challenge:	Compared to existing benchmarks, FinanceReasoning provides three key advancements: (1) credibility; (2) comprehensiveness; (3) numerical precision; (4) complexity; (5) complexity; and (6) complexity.
Approach:	They propose a benchmark to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems.
Outcome:	The proposed benchmark exceeds existing benchmarks in 67.8% of financial concepts and formulas and is credible, comprehensive, and challenging.

Copied to clipboard

Yingqian Min, Kun Zhou, Dawei Gao, Xin Zhao, He Hu, Yaliang Li

TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice (2026.acl-long)

Challenge:	Existing methods to improve sentence representation learning (SRL) ignore the potential interference problems across tasks and instances.
Approach:	They propose a multi-task instruction tuning method that arranges the order of multi- task data for training to minimize interference risks.
Outcome:	The proposed method can boost the performance of state-of-the-art methods.

Copied to clipboard

Gang Hu, Yating Chen, Haiyan Ding, Wang Gao, Huang Jiajia, Min Peng, Qianqian Xie, Kun Yue

Challenge:	Large Language Models excel in general domains but lack real-world practical capabilities.
Approach:	They propose a benchmark for Chinese taxation practice that combines 10 traditional application tasks with 3 pioneering real-world scenarios.
Outcome:	The proposed benchmark combines 10 traditional tasks with 3 pioneering real-world scenarios.

Improve Student’s Reasoning Generalizability through Cascading Decomposed CoTs Distillation (2024.emnlp-main)

Copied to clipboard

Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Challenge:	Existing studies have tried to distill these capabilities into smaller language models (SLMs) however, these capabilities are often associated with more parameters, which is not practical to emergent in smaller models.
Approach:	They propose to decompose the traditional single-step learning process into two cascaded learning steps by restructuring the training objectives and concatenating the question with the rationale as input.
Outcome:	Extensive experiments show that the proposed method improves reasoning generalizability and diversity of the model.

Copied to clipboard

Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang

Responsible & Trustworthy NLP

Challenge:	Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach:	AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome:	Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .

STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)

Copied to clipboard

Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma

Capture the Key in Reasoning to Enhance CoT Distillation Generalization (2025.acl-long)

Challenge:	Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation.
Approach:	They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset.
Outcome:	The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations.

Copied to clipboard

Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Graph Hawkes Transformer for Extrapolated Reasoning on Temporal Knowledge Graphs (2022.emnlp-main)

Challenge:	Existing distillation methods for Large Language Models (LLMs) focus on fine-tuning student SLMs on correct data, resulting in students struggling to learn the key instead of analyzing mistakes according to correct solutions.
Approach:	They propose a method that exposes key reasoning steps rather than simple fine-tuning students' CoTs data by using a set of prompts with similar reasoning paths but divergent conclusions.
Outcome:	The proposed method improves student SLMs' ability to learn key reasoning steps rather than fine-tuning them on teacher data.

Copied to clipboard

Haohai Sun, Shangyi Geng, Jialun Zhong, Han Hu, Kun He

YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)

Challenge:	Existing methods for entity prediction cannot predict when an event will occur . there are many facts not related to the query that can confuse the model .
Approach:	They propose a temporal knowledge Graph reasoning model based on Graph Hawkes Transformer . the model captures instantaneous structural and temporal evolution information .
Outcome:	The proposed model performs much better under long-term evolution scenarios.

Copied to clipboard

Hu Yiwen, Huatong Song, Jie Chen, Jia Deng, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Yang Lu, Xu Miao, Xin Zhao, Ji-Rong Wen

CoEvo: Coevolution of LLM and Retrieval Model for Domain-Specific Information Retrieval (2025.emnlp-main)

Challenge:	prevailing pre-training approaches for large language models involve several complexities.
Approach:	They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data .
Outcome:	The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data .

Copied to clipboard

Ang Li, Yiquan Wu, Yinghao Hu, Lizhi Qing, Shihang Wang, Chengyuan Liu, Tao Wu, Adam Jatowt, Ming Cai, Fei Wu, Kun Kuang

Information Retrieval

Challenge:	Recent methods to enhance queries by generating intermediary elements can degrade retrieval performance . combining LLMs and retrievers can be difficult, resulting in unreliable or irrelevant intermediaries .
Approach:	They propose a framework that facilitates the coevolution of large language models and retrieval models.
Outcome:	The proposed framework facilitates the coevolution of LLMs and retrieval models.

Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression (2026.acl-long)

Copied to clipboard

Liang Zhao, Xiaocheng Feng, Weihong Zhong, Lei Huang, Kun Zhu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

Challenge:	Recent methods to reduce the KV cache size fail to identify crucial KVs for generation while excluding others accurately, resulting in severe information loss.
Approach:	They propose an intention-aware KV cache eviction method that identifies and retains crucial KVs according to the attention distribution of intention, which semantically reflects the user’s goal and determines which part of the context is relevant.
Outcome:	The proposed method can maintain the model performance while reducing the KV cache size from 128K to 2K, leading to a 6.3x increase in decoding speed and 7.8x enhancement in memory efficiency compared to the default setting.

CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability (2023.emnlp-main)

Copied to clipboard

Minxuan Lv, Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Robustness in NLP

Challenge:	Neural network models are vulnerable to adversarial examples, and current methods based on adversarially transferable models rely on substitute models, which can be impractical and costly in real-world scenarios due to the unavailability of training data and the victim model’s structural details.
Approach:	They propose a novel approach that directly constructs adversarial examples by extracting transferable features across various tasks.
Outcome:	The proposed approach achieves superior attack performance with small cost on ten datasets and demonstrates that it is a novel approach.

DORA: Dynamic Optimization Prompt for Continuous Reflection of LLM-based Agent (2025.coling-main)

Copied to clipboard

Kun Li, Tingzhang Zhao, Wei Zhou, Songlin Hu

ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation (2025.findings-emnlp)

Challenge:	Existing studies have shown that reflection can enhance performance, but our investigation reveals an undesirable pattern in reflection framework: effective self-reflection occurs primarily at the beginning of iterations, with subsequent attempts failing to produce further improvements.
Approach:	They propose a framework that generates task-adaptive reflection advice using an external open-source small language model.
Outcome:	The proposed framework generates task-adaptive and diverse reflection advice in MiniWoB++ and Alfworld environments.

Copied to clipboard

Siying Zhou, Yiquan Wu, Hui Chen, Xueyu Hu, Kun Kuang, Adam Jatowt, Chunyan Zheng, Fei Wu

Challenge:	Currently, legal claims are not being used by non-professionals.
Approach:	They construct a dataset for Chinese legal claim generation task and then use it to evaluate the generated claims.
Outcome:	The proposed dataset is the first for the Chinese legal claim generation task and will be made publicly available.

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Copied to clipboard

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering (2025.coling-main)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

Yinghao Hu, Leilei Gan, Wenyi Xiao, Kun Kuang, Fei Wu

CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning (2026.acl-long)

Challenge:	Hallucination remains a critical challenge in large language models (LLMs) in high-stake domains such as legal question answering.
Approach:	They propose a method to mitigate hallucination in legal question answering by using behavior cloning and a novel Hard Sample-aware Direct Preference Optimization.
Outcome:	The proposed method improves non-hallucinated Statute Rate, Statute Relevance Rate, Legal Claim Truthfulness, and traditional metrics.

Copied to clipboard

Zhenpeng Su, Leiyu Pan, Minxuan Lv, Yuntao Li, Wenping Hu, Fuzheng Zhang, Kun Gai, Guorui Zhou

SplitThenMerge: Token-Level Skill-Compositional Sparse Mixture-of-Experts for Complex Domain-Specific Tasks (2026.findings-acl)

Challenge:	Existing methods for proximal policy optimization discard valuable gradient signals from low-probability tokens due to the clipping mechanism.
Approach:	They propose an algorithm that reintroduces gradients from clipped tokens in native PPO in a gentle and bounded manner.
Outcome:	The proposed algorithm outperforms strong baselines on reasoning benchmarks on different model scales.

Copied to clipboard

Yuting Huang, Jiawen Zhang, Yiquan Wu, Yinghao Hu, Fei Wu, Kun Kuang

Challenge:	Existing domain adaptation methods train heterogeneous skills together, making it difficult to reliably coordinate multiple skills when solving complex tasks.
Approach:	They propose a framework that decomposes domain competence into atomic skills and composes them dynamically during generation.
Outcome:	The proposed framework decomposes domain competence into atomic skills, trains them independently, and composes them dynamically during generation.

OTExtSum: Extractive Text Summarisation with Optimal Transport (2022.findings-naacl)

Copied to clipboard

Peggy Tang, Kun Hu, Rui Yan, Lei Zhang, Junbin Gao, Zhiyong Wang

Information Extraction & Text Mining

Challenge:	Extractive text summarisation aims to select salient sentences from a document to form a short yet informative summary.
Approach:	They propose to formulate extractive text summarisation as an Optimal Transport (OT) problem and use it to obtain an optimal summary that minimises the transportation cost to a given document.
Outcome:	The proposed method outperforms state-of-the-art methods and learning-based methods on multiNews, PubMed, BillSum, and CNN/DM datasets.

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs (2025.emnlp-main)

Copied to clipboard

Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Wenwu Ou, Di Zhang, Kun Gai, Songlin Hu

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges (2025.findings-acl)

Challenge:	Existing sparsification methods like pruning can lose model knowledge through parameter removal.
Approach:	They propose a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.
Outcome:	The proposed approach achieves superior performance across language modeling and downstream tasks under equivalent computational constraints.

Copied to clipboard

Yibo Yan, Jiamin Su, Jianxiang He, Fangteng Fu, Xu Zheng, Yuanhuiyi Lyu, Kun Wang, Shen Wang, Qingsong Wen, Xuming Hu

Dynamic Simulation Framework for Disinformation Dissemination and Correction With Social Bots (2025.findings-emnlp)

Challenge:	This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models . integrating large language model with mathematical reasoning tasks is becoming significant as AI advances .
Approach:	They review over 200 studies published since 2021 and examine the state-of-the-art developments in Math-LLMs . they identify five major challenges hindering the realization of AGI in this domain .
Outcome:	The authors examine the state-of-the-art developments in Math-LLMs with a focus on multimodal settings.

Copied to clipboard

Boyu Qiao, Kun Li, Wei Zhou, Songlin Hu

LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Challenge:	Current studies rely on simplistic user and network modeling and neglect dynamic behavior of bots.
Approach:	They propose a multi-agent-based framework for disinformation dissemination . it incorporates both malicious and legitimate bots and allows quantitative evaluation of correction strategies.
Outcome:	The proposed framework incorporates both malicious and legitimate bots and their controlled dynamic participation allows for quantitative analysis of correction strategies.

Copied to clipboard

Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen

Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond (2025.findings-emnlp)

Challenge:	a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach:	They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome:	The proposed library is based on extensive experiments in a variety of evaluation settings.

Copied to clipboard

Yinghao Hu, Yaoyao Yu, Leilei Gan, Bin Wei, Kun Kuang, Fei Wu

Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning (2026.findings-acl)

Challenge:	Experimental results show that Legal-R1 delivers competitive performance across diverse tasks.
Approach:	They propose to evaluate 12 large language models across 17 legal tasks across statutory and case-law traditions to determine their general reasoning performance.
Outcome:	The proposed model performs well across 17 legal tasks across statutory and case-law traditions.

Copied to clipboard

Zhenpeng Su, Leiyu Pan, Minxuan Lv, Tiehua Mei, Zijia Lin, Yuntao Li, Wenping Hu, Ruiming Tang, Kun Gai, Guorui Zhou

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Challenge:	Large language model post-training often adopts an off-policy training paradigm . however, the off-poliicy training model introduces distribution shifts that push the policy beyond the trust region.
Approach:	They propose to use the entropy ratio as a global metric to measure the relative change in policy exploration throughout updates.
Outcome:	Experiments show that the proposed metric improves performance across multiple benchmarks.

Copied to clipboard

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA (2026.findings-acl)

Challenge:	Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs.
Approach:	They propose a framework that integrates dialogue, reasoning, and personalized recommendation.
Outcome:	Experiments across public benchmarks show state-of-the-art performance.

Copied to clipboard

Meng Zhang, Ruochun Jin, Yuanxi Peng, Wenjing Yang, Haotian Wang, Liting Sun, Kun Hu, Silin Yang, Zhang Ke-di

Multimodality

Challenge:	Text-to-SQL models struggle with complex analytical tasks such as generating simple SQL queries.
Approach:	They propose a text-to-sql model that leverages Python as a procedural reasoning pivot to enhance both complex SQL generation and tabular reasoning.
Outcome:	The proposed model outperforms baseline models on six text-to-SQL benchmarks by 6.44% on average while maintaining good capability on three tableQA benchmarks.

Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning (2026.acl-long)

Copied to clipboard

YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin