Author name cluster

Weilin Luo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

AAAI Conference 2026 Conference Paper

Large Language Models Struggle with Unreasonability in Math Problems

Jingyuan Ma
Damai Dai
Zihang Yuan
Rui Li
Weilin Luo
Bin Wang
Qun Liu
Lei Sha

Large Language Models (LLMs) have shown remarkable success on a wide range of math and reasoning benchmarks. However, we observe that they often struggle when faced with unreasonable math problems. Instead of recognizing these issues, models frequently proceed as if the problem is well-posed, producing incorrect answers or falling into overthinking and verbose self-correction. To systematically investigate this overlooked vulnerability, we propose the Unreasonable Math Problems (UMP) benchmark, designed to evaluate LLMs' ability to detect and respond to unreasonable math problem statements. Based on extensive experiments covering 19 LLMs, we find that even state-of-the-art general models like GPT-4o struggle on UMP. While reasoning models such as DeepSeek-R1 demonstrate a higher sensitivity to unreasonable inputs, this often comes at the cost of generating overly long and meaningless responses that fail to converge. We further find that prompting and fine-tuning enhance the detection of unreasonable inputs, with minor and acceptable trade-offs, making them practical solutions in this challenging setting.

PDF Details DOI

AAAI Conference 2026 Conference Paper

RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection

Yixin Yang
Qingxiu Dong
Linli Yao
Fangwei Zhu
Weilin Luo
Bin Wang
Zhifang Sui

Data selection for instruction tuning is crucial for improving the performance of large language models (LLMs) while reducing training costs. In this paper, we propose Refined Contribution Measurement with In-Context Learning (RICo), a novel gradient-free method that quantifies the fine-grained contribution of individual samples to both task-level and global-level model performance. RICo enables more accurate identification of high-contribution data, leading to better instruction tuning. We also introduce a lightweight selection paradigm trained on RICo scores, enabling scalable data selection with strictly linear inference complexity. Extensive experiments on 3 LLMs across 12 benchmarks and 5 pairwise evaluation sets demonstrate the effectiveness of RICo. Remarkably, on LLaMA3.1-8B, models trained in 15% of RICo-selected data outperform full datasets by 5.42 percentage points and exceed the best performance of widely used selection methods by 1.48 percentage points. We further analyze high-contribution samples selected by RICo, which show both diverse tasks and appropriate difficulty levels, rather than merely the most difficult cases.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Dynamic Configuration for Cutting Plane Separators via Reinforcement Learning on Incremental Graph

Mingxuan Ye
Jie Wang
Fangzhou Fangzhou
Zhihai Wang
Yufei Kuang
Xijun Li
Weilin Luo
Jianye Hao

Cutting planes (cuts) are essential for solving mixed-integer linear programming (MILP) problems, as they tighten the feasible solution space and accelerate the solving process. Modern MILP solvers offer diverse cutting plane separators to generate cuts, enabling users to leverage their potential complementary strengths to tackle problems with different structures. Recent machine learning approaches learn to configure separators based on problem-specific features, selecting effective separators and deactivating ineffective ones to save unnecessary computing time. However, they ignore the dynamics of separator efficacy at different stages of cut generation and struggle to adapt the configurations for the evolving problems after multiple rounds of cut generation. To address this challenge, we propose a novel dyn amic sep arator configuration ( DynSep ) method that models separator configuration in different rounds as a reinforcement learning task, making decisions based on an incremental triplet graph updated by iteratively added cuts. Specifically, we tokenize the incremental subgraphs and utilize a decoder-only Transformer as our policy to autoregressively predict when to halt separation and which separators to activate at each round. Evaluated on synthetic and large-scale real-world MILP problems, DynSep speeds up average solving time by 64% on easy and medium datasets, and reduces primal-dual gap integral within the given time limit by 16% on hard datasets. Moreover, experiments demonstrate that DynSep well generalizes to MILP instances of significantly larger sizes than those seen during training.

PDF Details

AAAI Conference 2024 Conference Paper

End-to-End Learning of LTLf Formulae by Faithful LTLf Encoding

Hai Wan
Pingjia Liang
Jianfeng Du
Weilin Luo
Rongzhen Ye
Bo Peng

It is important to automatically discover the underlying tree-structured formulae from large amounts of data. In this paper, we examine learning linear temporal logic on finite traces (LTLf) formulae, which is a tree structure syntactically and characterizes temporal properties semantically. Its core challenge is to bridge the gap between the concise tree-structured syntax and the complex LTLf semantics. Besides, the learning quality is endangered by explosion of the search space and wrong search bias guided by imperfect data. We tackle these challenges by proposing an LTLf encoding method to parameterize a neural network so that the neural computation is able to simulate the inference of LTLf formulae. We first identify faithful LTLf encoding, a subclass of LTLf encoding, which has a one-to-one correspondence to LTLf formulae. Faithful encoding guarantees that the learned parameter assignment of the neural network can directly be interpreted to an LTLf formula. With such an encoding method, we then propose an end-to-end approach, TLTLf, to learn LTLf formulae through neural networks parameterized by our LTLf encoding method. Experimental results demonstrate that our approach achieves state-of-the-art performance with up to 7% improvement in accuracy, highlighting the benefits of introducing the faithful LTLf encoding.

PDF Details DOI

ICLR Conference 2024 Conference Paper

L2P-MIP: Learning to Presolve for Mixed Integer Programming

Chang Liu 0021
Zhichen Dong
Haobo Ma
Weilin Luo
Xijun Li
Bowen Pang
Jia Zeng
Junchi Yan

Modern solvers for solving mixed integer programming (MIP) often rely on the branch-and-bound (B&B) algorithm which could be of high time complexity, and presolving techniques are well designed to simplify the instance as pre-processing before B&B. However, such presolvers in existing literature or open-source solvers are mostly set by default agnostic to specific input instances, and few studies have been reported on tailoring presolving settings. In this paper, we aim to dive into this open question and show that the MIP solver can be indeed largely improved when switching the default instance-agnostic presolving into instance-specific presolving. Specifically, we propose a combination of supervised learning and classic heuristics to achieve efficient presolving adjusting, avoiding tedious reinforcement learning. Notably, our approach is orthogonal from many recent efforts in incorporating learning modules into the B&B framework after the presolving stage, and to our best knowledge, this is the first work for introducing learning to presolve in MIP solvers. Experiments on multiple real-world datasets show that well-trained neural networks can infer proper presolving for arbitrary incoming MIP instances in less than 0.5s, which is neglectable compared with the solving time often hours or days.

Details

AAAI Conference 2023 Conference Paper

A Noise-Tolerant Differentiable Learning Approach for Single Occurrence Regular Expression with Interleaving

Rongzhen Ye
Tianqu Zhuang
Hai Wan
Jianfeng Du
Weilin Luo
Pingjia Liang

We study the problem of learning a single occurrence regular expression with interleaving (SOIRE) from a set of text strings possibly with noise. SOIRE fully supports interleaving and covers a large portion of regular expressions used in practice. Learning SOIREs is challenging because it requires heavy computation and text strings usually contain noise in practice. Most of the previous studies only learn restricted SOIREs and are not robust on noisy data. To tackle these issues, we propose a noise-tolerant differentiable learning approach SOIREDL for SOIRE. We design a neural network to simulate SOIRE matching and theoretically prove that certain assignments of the set of parameters learnt by the neural network, called faithful encodings, are one-to-one corresponding to SOIREs for a bounded size. Based on this correspondence, we interpret the target SOIRE from an assignment of the set of parameters of the neural network by exploring the nearest faithful encodings. Experimental results show that SOIREDL outperforms the state-of-the-art approaches, especially on noisy data.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Bridging LTLf Inference to GNN Inference for Learning LTLf Formulae

Weilin Luo
Pingjia Liang
Jianfeng Du
Hai Wan
Bo Peng
Delong Zhang

Learning linear temporal logic on finite traces (LTLf ) formulae aims to learn a target formula that characterizes the highlevel behavior of a system from observation traces in planning. Existing approaches to learning LTLf formulae, however, can hardly learn accurate LTLf formulae from noisy data. It is challenging to design an efficient search mechanism in the large search space in form of arbitrary LTLf formulae while alleviating the wrong search bias resulting from noisy data. In this paper, we tackle this problem by bridging LTLf inference to GNN inference. Our key theoretical contribution is showing that GNN inference can simulate LTLf inference to distinguish traces. Based on our theoretical result, we design a GNN-based approach, GLTLf, which combines GNN inference and parameter interpretation to seek the target formula in the large search space. Thanks to the non-deterministic learning process of GNNs, GLTLf is able to cope with noise. We evaluate GLTLf on various datasets with noise. Our experimental results confirm the effectiveness of GNN inference in learning LTLf formulae and show that GLTLf is superior to the state-of-the-art approaches.

PDF Details

AAAI Conference 2022 Conference Paper

Improving Local Search Algorithms via Probabilistic Configuration Checking

Weilin Luo
Rongzhen Ye
Hai Wan
Shaowei Cai
Biqing Fang
Delong Zhang

Configuration checking (CC) has been confirmed to alleviate the cycling problem in local search for combinatorial optimization problems (COPs). When using CC heuristics in local search for graph problems, a critical concept is the configuration of the vertices. All existing CC variants employ either 1- or 2-level neighborhoods of a vertex as its configuration. Inspired by the idea that neighborhoods with different levels should have different contributions to solving COPs, we propose the probabilistic configuration (PC), which introduces probabilities for neighborhoods at different levels to consider the impact of neighborhoods of different levels on the CC strategy. Based on the concept of PC, we first propose probabilistic configuration checking (PCC), which can be developed in an automated and lightweight favor. We then apply PCC to two classic COPs which have been shown to achieve good results by using CC, and our preliminary results confirm that PCC improves the existing algorithms because PCC alleviates the cycling problem.

PDF Details

IJCAI Conference 2022 Conference Paper

Teaching LTLf Satisfiability Checking to Neural Networks

Weilin Luo
Hai Wan
Jianfeng Du
Xiaoda Li
Yuze Fu
Rongzhen Ye
Delong Zhang

Linear temporal logic over finite traces (LTLf) satisfiability checking is a fundamental and hard (PSPACE-complete) problem in the artificial intelligence community. We explore teaching end-to-end neural networks to check satisfiability in polynomial time. It is a challenge to characterize the syntactic and semantic features of LTLf via neural networks. To tackle this challenge, we propose LTLfNet, a recursive neural network that captures syntactic features of LTLf by recursively combining the embeddings of sub-formulae. LTLfNet models permutation invariance and sequentiality in the semantics of LTLf through different aggregation mechanisms of sub-formulae. Experimental results demonstrate that LTLfNet achieves good performance in synthetic datasets and generalizes across large-scale datasets. They also show that LTLfNet is competitive with state-of-the-art symbolic approaches such as nuXmv and CDLSC.

PDF Details DOI