Author name cluster

Zhaoqun Li

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.

5 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

IneqSearch: Hybrid Reasoning for Olympiad Inequality Proofs

Zhaoqun Li
Beishui Liao
Qiwei Ye

Mathematicians have long employed decomposition techniques to prove inequalities, yet automating this process remains a significant challenge in computational mathematics. We introduce IneqSearch, a hybrid reasoning system that integrates symbolic computation with large language models (LLMs) to address this challenge. IneqSearch reformulates inequality proving as a structured search problem: identifying appropriate combinations of theorems that decompose expressions into non-negative components. The system combines a symbolic solver for deductive reasoning with an LLM-based agent for constructive proof exploration, effectively implementing methodologies observed in formal mathematical practice. A key contribution of IneqSearch is its iterative learning mechanism that systematically incorporates newly proven results into its theorem database, enabling knowledge acquisition during practice that enhances its capabilities without requiring human intervention. In empirical evaluation on 437 Olympiad-level inequalities, IneqSearch successfully proves 342 problems, significantly outperforming existing methods and demonstrating the effectiveness of integrating symbolic and neural approaches for mathematical reasoning.

PDF Details

ECAI Conference 2025 Conference Paper

LLM-ASPIC +: A Neuro-Symbolic Framework for Defeasible Reasoning

Xiaotong Fang
Zhaoqun Li
Chen Chen
Beishui Liao

Large language models (LLMs) excel at complex reasoning and achieve human-like performance in many natural language processing tasks. However, they still struggle to reason effectively when faced with inconsistent or contradictory information. This capability gap raises significant concerns for real-world applications where reliable decision-making depends on reconciling conflicting evidence, such as legal analysis, medical diagnosis, and commonsense reasoning. In this paper, we focus on defeasible reasoning in natural language, a task that challenges LLMs to handle and resolve contradictory information. To improve the defeasible reasoning capability of LLMs, we propose LLM-ASPIC+, a framework combining neural language understanding with formal argumentation. Our framework harnesses LLMs’ capacity for grounding and contextual reasoning while integrating formal argumentation frameworks to establish systematic conflict resolution mechanisms lacking in LLMs. We also create MineQA, a newly synthesized dataset designed to evaluate multi-step defeasible reasoning under both strict and defeasible rules. LLM-ASPIC+ achieves state-of-the-art results on multi-step defeasible reasoning, with 87. 1% accuracy on BoardGameQA-2 and 82. 6% on BoardGameQA-3. These results show that integrating neural language models with formal argumentation effectively supports defeasible reasoning in natural language.

Details

NeurIPS Conference 2025 Conference Paper

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Xeron Du
Yifan Yao
Kaijing Ma
Bingli Wang
Tianyu Zheng
Minghao Liu
Yiming Liang
Xiaolong Jin

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e. g. , the reasoning-focused model Gemini-2. 5-Pro achieved the highest accuracy of 63. 56% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

PDF Details

AAAI Conference 2019 Conference Paper

Angular Triplet-Center Loss for Multi-View 3D Shape Retrieval

Zhaoqun Li
Cheng Xu
Biao Leng

How to obtain the desirable representation of a 3D shape, which is discriminative across categories and polymerized within classes, is a significant challenge in 3D shape retrieval. Most existing 3D shape retrieval methods focus on capturing strong discriminative shape representation with softmax loss for the classification task, while the shape feature learning with metric loss is neglected for 3D shape retrieval. In this paper, we address this problem based on the intuition that the cosine distance of shape embeddings should be close enough within the same class and far away across categories. Since most of 3D shape retrieval tasks use cosine distance of shape features for measuring shape similarity, we propose a novel metric loss named angular triplet-center loss, which directly optimizes the cosine distances between the features. It inherits the triplet-center loss property to achieve larger inter-class distance and smaller intra-class distance simultaneously. Unlike previous metric loss utilized in 3D shape retrieval methods, where Euclidean distance is adopted and the margin design is difficult, the proposed method is more convenient to train feature embeddings and more suitable for 3D shape retrieval. Moreover, the angle margin is adopted to replace the cosine margin in order to provide more explicit discriminative constraints on an embedding space. Extensive experimental results on two popular 3D object retrieval benchmarks, ModelNet40 and ShapeNetCore 55, demonstrate the effectiveness of our proposed loss, and our method has achieved state-ofthe-art results on various 3D shape datasets.

PDF Details

IJCAI Conference 2019 Conference Paper

Rethinking Loss Design for Large-scale 3D Shape Retrieval

Zhaoqun Li
Cheng Xu
Biao Leng

Learning discriminative shape representations is a crucial issue for large-scale 3D shape retrieval. In this paper, we propose the Collaborative Inner Product Loss (CIP Loss) to obtain ideal shape embedding that discriminative among different categories and clustered within the same class. Utilizing simple inner product operation, CIP loss explicitly enforces the features of the same class to be clustered in a linear subspace, while inter-class subspaces are constrained to be at least orthogonal. Compared to previous metric loss functions, CIP loss could provide more clear geometric interpretation for the embedding than Euclidean margin, and is easy to implement without normalization operation referring to cosine margin. Moreover, our proposed loss term can combine with other commonly used loss functions and can be easily plugged into existing off-the-shelf architectures. Extensive experiments conducted on the two public 3D object retrieval datasets, ModelNet and ShapeNetCore 55, demonstrate the effectiveness of our proposal, and our method has achieved state-of-the-art results on both datasets.

PDF Details