Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Let’s Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models
Published in EMNLP2023 (Findings), 2023
Data Synthesis is a promising way to train a small model with very little labeled data. One approach for data synthesis is to leverage the rich knowledge from large language models to synthesize pseudo training examples for small models, making it possible to achieve both data and compute efficiency at the same time. However, a key challenge in data synthesis is that the synthesized dataset often suffers from a large distributional discrepancy from the real task data distribution. Thus, in this paper, we propose Synthesis Step by Step (S3), a data synthesis framework that shrinks this distribution gap by iteratively extrapolating the errors made by a small model trained on the synthesized dataset on a small real-world validation dataset using a large language model. Extensive experiments on multiple NLP tasks show that our approach improves the performance of a small model by reducing the gap between the synthetic dataset and the real data, resulting in significant improvement compared to several baselines: 9.48% improvement compared to ZeroGen and 2.73% compared to GoldGen, and at most 15.17% improvement compared to the small model trained on human-annotated data.
DragVideo: Interactive Drag-style Video Editing
Published in ECCV2024, 2024
Video generation models have shown their superior ability to generate photo-realistic video. However, how to accurately control (or edit) the video remains a formidable challenge. The main issues are: 1) how to perform direct and accurate user control in editing; 2) how to execute editings like changing shape, expression, and layout without unsightly distortion and artifacts to the edited content; and 3) how to maintain spatio-temporal consistency of video after editing. To address the above issues, we propose DragVideo, a general drag-style video editing framework. Inspired by DragGAN, DragVideo addresses issues 1) and 2) by proposing the drag-style video latent optimization method which gives desired control by updating noisy video latent according to drag instructions through video-level drag objective function. We amend issue 3) by integrating the video diffusion model with sample-specific LoRA and Mutual Self-Attention in DragVideo to ensure the edited result is spatio-temporally consistent. We also present a series of testing examples for drag-style video editing and conduct extensive experiments across a wide array of challenging editing tasks, such as motion, skeleton editing, etc, underscoring DragVideo can edit video in an intuitive, faithful to the user’s intention manner, with nearly unnoticeable distortion and artifacts, while maintaining spatio-temporal consistency. While traditional prompt-based video editing fails to do the former two and directly applying image drag editing fails in the last, DragVideo’s versatility and generality are emphasized. Github link: this https URL.
TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts
Published in EMNLP 2024 (Main), 2024
Proving mathematical theorems using computer-verifiable formal languages like Lean significantly impacts mathematical reasoning. One approach to formal theorem proving involves generating complete proofs using Large Language Models (LLMs) based on Natural Language (NL) proofs. Similar methods have shown promising results in code generation. However, most modern LLMs exhibit suboptimal performance due to the scarcity of aligned NL and Formal Language (FL) theorem-proving data. This scarcity results in a paucity of methodologies for training LLMs and techniques to fully utilize their capabilities in composing formal proofs. To address the challenges, this paper proposes TheoremLlama, an end-to-end framework to train a general-purpose LLM to become a Lean4 expert. This framework encompasses NL-FL aligned dataset generation methods, training approaches for the LLM formal theorem prover, and techniques for LLM Lean4 proof writing. Using the dataset generation method, we provide Open Bootstrapped Theorems (OBT), an NL-FL aligned and bootstrapped dataset. A key innovation in this framework is the NL-FL bootstrapping method, where NL proofs are integrated into Lean4 code for training datasets, leveraging the NL reasoning ability of LLMs for formal reasoning. The TheoremLlama framework achieves cumulative accuracies of 36.48% and 33.61% on MiniF2F-Valid and Test datasets respectively, surpassing the GPT-4 baseline of 22.95% and 25.41%. We have also open-sourced our model checkpoints and generated dataset, and will soon make all the code publicly available.
SR-PredictAO: Session-based Recommendation with High-Capability Predictor Add-On
Published in ICDM 2024 (Oral), 2024
Session-based recommendation, aiming at making the prediction of the user’s next item click based on the information in a single session only even in the presence of some random user’s behavior, is a complex problem. This complex problem requires a high-capability model of predicting the user’s next action. Most (if not all) existing models follow the encoder-predictor paradigm where all studies focus on how to optimize the encoder module extensively in the paradigm but they ignore how to optimize the predictor module. In this paper, we discover the existing critical issue of the low-capability predictor module among existing models. Motivated by this, we propose a novel framework called Session-based Recommendation with Predictor Add-On (SR-PredictAO). In this framework, we propose a high-capability predictor module which could alleviate the effect of random user’s behavior for prediction. It is worth mentioning that this framework could be applied to any existing models, which could give opportunities for further optimizing the framework. Extensive experiments on two real benchmark datasets for three state-of-the-art models show that SR-PredictAO out-performs the current state-of-the-art model by up to 2.9% in HR@20 and 2.3% in MRR@20. More importantly, the improvement is consistent across almost all the existing models on all datasets, which could be regarded as a significant contribution in the field.
MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
Published in ICML 2025, 2025
Solving mathematical problems using computer-verifiable languages like Lean has significantly impacted the mathematical and computer science communities. State-of-the-art methods utilize a single Large Language Model (LLM) to generate complete proof or perform tree search, but they fail to balance these tasks. We propose MA-LoT: Model-CollAboration Lean-based Long Chain-of-Thought, a comprehensive framework for Lean4 theorem proving to solve this issue. It separates the cognition tasks of general NL for whole-proof generation and error analysis for proof correction using the model-collaboration method. We achieve this by structured interaction of the LLM and Lean4 verifier in Long CoT. To implement the framework, we propose the novel LoT-Transfer Learning training-inference pipeline, which enables the Long CoT thinking capability to LLMs without special data annotation. Extensive experiment shows that our framework achieves a 61.07% accuracy rate on the Lean4 version of the MiniF2F-Test dataset, largely outperforming DeepSeek-V3 (33.61%), single-model tree search (InternLM-Step-Prover, 50.70%), and whole-proof generation (Godel-Prover, 55.33%) baselines. Furthermore, our findings highlight the potential of combining Long CoT with formal verification for a more insightful generation in a broader perspective.
FANS: Formal Answer Selection for LLM Natural Language Math Reasoning Using Lean4
Published in EMNLP 2025 (Main), 2025
Large Language Models (LLMs) have displayed astonishing abilities in various tasks, especially in text generation, classification, question answering, etc. However, the reasoning ability of LLMs still faces many debates, especially in math reasoning. The inherent ambiguity of Natural Language (NL) limits LLMs’ ability to perform verifiable reasoning, making the answers lack coherence and trustworthy support. To tackle the above challenges, we propose a novel framework named FANS: Formal ANswer Selection for LLM Natural Language Math Reasoning Using Lean4. It is a pioneering framework that utilizes Lean4 to enhance LLMs’ NL math reasoning ability. In particular, given an NL math question and LLM-generated answers, FANS first translates it into Lean4 theorem statements. Then it invokes another Lean4 prover LLM to produce proofs, and finally verifies the proofs by the Lean4 compiler. Answers are selected based on the verifications. It enhances LLMs’ NL math ability in providing a computer-verifiable solution for its correct answer and proposes an alternative method for answer selection beyond the reward model-based ones. Our experiments demonstrate the effectiveness of FANS with an improvement of nearly 2% across several math benchmarks, and even higher further based on reward models or in subfields such as algebra and number theory that Lean4 is better at. The code is available in https://github.com/MaxwellJryao/FANS.
Let’s Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM’s Math Capability
Published in EMNLP 2025 (Main), 2025
Enhancing the mathematical reasoning capabilities of LLMs has garnered significant attention in both the mathematical and computer science communities. Recent works have made substantial progress in both Natural Language (NL) reasoning and Formal Language (FL) reasoning by leveraging the potential of pure Reinforcement Learning (RL) methods on base models. However, RL approaches struggle to impart new capabilities not presented in the base model, highlighting the need to integrate more knowledge like FL into NL math reasoning effectively. Yet, this integration is challenging due to inherent disparities in problem structure and reasoning format between NL and FL. To address these challenges, we introduce NL-FL HybridReasoning (NFL-HR), an end-to-end framework designed to incorporate the FL expert into NL math problem-solving. To bridge the NL and FL input format gap, we propose the NL-FL Problem Alignment method, which reformulates the Question-Answering (QA) problems in NL as existence theorems in FL. Subsequently, the Mixed Problem Input technique we provide enables the FL reasoner to handle both QA and existence problems concurrently. Lastly, we mitigate the NL and FL output format gap in reasoning through an LLM-based Answer Extraction mechanism. Comprehensive experiments demonstrate that the NFL-HR framework achieves 89.80% and 84.34% accuracy rates on the MATH-500 and the AMC benchmarks, surpassing the NL baseline by 4.60% and 4.82%, respectively. Notably, some problems resolved by our framework remain unsolved by the NL baseline model even under a larger number of trials.
GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving
Published in ICLR 2026, 2026
Solving math problems through verifiable languages such as Lean has significantly impacted both the mathematics and computer science communities. Current state-of-the-art models are often trained with expensive online Reinforcement Learning (RL) or expert iteration. However, these approaches rely on fixed problem sets, which causes inefficient training and limits the model to tackle complex problems. To overcome these limitations, we propose GAR: Generative Adversarial Reinforcement learning, a comprehensive RL training framework that jointly trains the problem composer and solver in an adversarial loop. GAR introduces an implicit curriculum learning mechanism, which aligns task difficulty with the prover’s evolving capability. It thereby improves the training efficiency and enables stronger performance of proving advanced theorems. Experiments show that with GAR training, Goedel-Prover-V2-8B and DeepSeek-Prover-V2-7B achieve an average relative improvement in pass@32 of 4.20% on MiniF2F-Test benchmark, while DeepSeek-Prover-V2’s pass@32 on ProofNet-Test increases from 22.58% to 25.81%. Beyond formal proving, GAR establishes a general RL paradigm for co-evolution of problem generation and solving under verifiable environments. The training code for this paper is open-sourced here.
Lean4Physics: Comprehensive Reasoning Framework for College-level Physics in Lean4
Published in ICLR 2026, 2026
We present Lean4PHYS, a comprehensive reasoning framework for college-level physics problems in Lean4. Lean4PHYS includes LeanPhysBench, a college-level benchmark for formal physics reasoning in Lean4, which contains 200 hand-crafted and peer-reviewed statements derived from university textbooks and physics competition problems. To establish a solid foundation for formal reasoning in physics, we also introduce PhysLib, a community-driven repository containing fundamental unit systems and theorems essential for formal physics reasoning. Based on the benchmark and Lean4 repository we composed in Lean4PHYS, we report baseline results using major expert Math Lean4 provers and state-of-the-art closed-source models, with the best performance of DeepSeek-Prover-V2-7B achieving only 16% and Claude-Sonnet-4 achieving 35%. We also conduct a detailed analysis showing that our PhysLib can achieve an average improvement of 11.75% in model performance. This demonstrates the challenging nature of our LeanPhysBench and the effectiveness of PhysLib. To the best of our knowledge, this is the first study to provide a physics benchmark in Lean4.
Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
Published in Preprint, 2026
Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence. Despite recent advances in LLMs’ agentic capabilities, most agent systems still lack formal methods for specifying, verifying, and debugging their workflow and execution trajectories. This challenge mirrors a long-standing problem in mathematics, where the ambiguity of natural languages (NLs) motivates the development of formal languages (FLs). Inspired by this paradigm, we propose Lean4Agent, to the best of our knowledge, the first framework that uses Lean4, a dependent-type FL to model and verify agent behavior. Lean4Agent launches FormalAgentLib, an extensible Lean4 library for formally modeling and verifying agent workflows’ semantic consistency under explicit assumptions, and enabling localization of execution-time failures revealed by trajectories. Building on FormalAgentLib, we further develop LeanEvolve, which applies results in FormalAgentLib to revise workflows to enhance its capability. Extensive experiments on a hard problem subset of SWE-Bench-Verified and a subset of ELAIP-Bench across 5 leading LLMs indicate that the verification-passing workflows outperform the failing ones by an average of 11.94%, and LeanEvolve further improves SWE performance by 7.47% on average. Furthermore, Lean4Agent establishes a foundation for a new field of using expressive dependent-type FL to formally model and verify agent behavior.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.