Author name cluster

Nianmin Yao

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.

4 papers

1 author row

AAAI Conference 2026 Conference Paper

Counterfactual-based Cognitive Alignment In-Context Learning for Relation Extraction

Qibin Li
Shengyuan Bai
Nai Zhou
Nianmin Yao

Large Language Models (LLMs) have demonstrated remarkable In-Context learning (ICL) capabilities for relation extraction (RE). While ICL has shown promise in RE tasks, current approaches face challenges in example selection and utilization. These challenges stem from the misalignment between example selection methods and LLMs' inherent cognitive processing mechanisms, particularly in pattern recognition and relational reasoning. To address these limitations, we propose Counterfactual Cognitive Alignment (CCA), a novel framework that systematically enhances ICL performance in RE by aligning example selection with cognitive principles underlying human relational reasoning. The framework incorporates a cognitive-inspired counterfactual generation mechanism that creates semantically diverse yet relationally coherent examples, mirroring human "what-if" reasoning processes. Additionally, it employs a cognitive alignment approach that integrates structural identification features with semantic understanding to better align with LLMs cognitive processing patterns. Extensive experiments across multiple RE benchmarks reveal the effectiveness of our cognitive alignment approach through the synergistic integration of counterfactual reasoning and cognitively-guided selection.

PDF Details DOI

EAAI Journal 2025 Journal Article

Enhancing entity and relation extraction with dynamic hard negative augmentation framework

Qibin Li
Shengyuan Bai
Nai Zhou
Nianmin Yao

Entity and relation extraction, a fundamental task in information extraction, plays a crucial role in modeling unstructured text by identifying meaningful entities and their semantic relationships. While existing methods have shown effectiveness, they still face challenges in accurately identifying entity boundaries and extracting complex relationships. These challenges primarily arise from current contrastive learning approaches, which uniformly handle all negative samples in boundary detection and relation extraction without emphasizing the learning of hard negative samples. Additionally, the scarcity of hard negative samples limits the exploration of the state space near the anchors. To tackle these challenges, we introduce Dynamic Hard Negative Augmentation, an innovative framework designed to strategically explore and generate hard negative samples, thereby enhancing the learning of challenging cases through adaptive contrastive learning. During the negative sample augmentation process, we employ adversarial training to explore underrepresented areas of hard negative samples, generating a comprehensive coverage of the hard negative sample space to effectively explore the state space. We further introduce a dynamic enhancement mechanism that continuously optimizes the proportion of hard negative samples during training, ensuring targeted learning of these challenging cases.

Details DOI

AAAI Conference 2025 Conference Paper

Enhancing NLU in Large Language Models Using Adversarial Noisy Instruction Tuning

Shengyuan Bai
Qibin Li
Zhe Wang
Nai Zhou
Nianmin Yao

Instruction tuning has emerged as an effective approach that notably improves large language models (LLMs) performance, showing particular promise in natural language generation tasks by producing more diverse, coherent, and task-relevant outputs. However, extending instruction tuning to natural language understanding (NLU) tasks presents significant challenges, primarily due to the difficulty in achieving high-precision responses and the scarcity of large-scale, high-quality instruction data necessary for effective tuning. In this work, we introduce Adversarial Noisy Instruction Tuning (ANIT) to improve NLU performance on LLMs. First, we leverage low-resource techniques to construct noisy instruction datasets. Second, we employ semantic distortion-aware techniques to quantify the intensity of noise within these instructions. Last, we devise an adversarial training method that incorporates a noise response strategy to achieve noisy instruction tuning. ANIT enhances LLMs capability to detect and accommodate semantic distortions in noisy instructions, thereby augmenting their comprehension of task objectives and ability to generate more accurate responses. We evaluate our approach across diverse noisy instructions and semantic distortion quantification methods on multiple NLU tasks. Comprehensive empirical results demonstrate that our method consistently outperforms existing approaches across various experimental settings.

PDF Details DOI

TIST Journal 2023 Journal Article

A Joint Entity and Relation Extraction Model based on Efficient Sampling and Explicit Interaction

Qibin Li
Nianmin Yao
Nai Zhou
Jian Zhao
Yanan Zhang

Joint entity and relation extraction (RE) construct a framework for unifying entity recognition and relationship extraction, and the approach can exploit the dependencies between the two tasks to improve the performance of the task. However, the existing tasks still have the following two problems. First, when the model extracts entity information, the boundary is blurred. Secondly, there are mostly implicit interactions between modules, that is, the interactive information is hidden inside the model, and the implicit interactions are often insufficient in the degree of interaction and lack of interpretability. To this end, this study proposes a joint entity and relation extraction model (ESEI) based on E fficient S ampling and E xplicit I nteraction. We innovatively divide negative samples into sentences based on whether they overlap with positive samples, which improves the model’s ability to extract entity word boundary information by controlling the sampling ratio. In order to increase the explicit interaction ability between the models, we introduce a heterogeneous graph neural network (GNN) into the model, which will serve as a bridge linking the entity recognition module and the relation extraction module, and enhance the interaction between the modules through information transfer. Our method substantially improves the model’s discriminative power on entity extraction tasks and enhances the interaction between relation extraction tasks and entity extraction tasks. Experiments show that the method is effective, we validate our method on four datasets, and for joint entity and relation extraction, our model improves the F1 score on multiple datasets.

Details DOI