Chaodong Tong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chaodong Tong has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Kun Peng
Institute of Information Engineering Chinese Academy of Sciences China
4 shared publications - Lei Jiang
Institute of Information Engineering Chinese Academy of Sciences Beijing China
4 shared publications Cong Cao
Institute of Information Engineering, Chinese Academy of Sciences
2 shared publicationsGuanlin Wu
College of Systems Engineering, National University of Defense Technology
2 shared publicationsHao Peng
School of Cyber Science and Technology, Beihang University
2 shared publicationsLei Jiang
Institute of Information Engineering, Chinese Academy of Sciences
2 shared publications
Latest Publications
- Open Access
HaluNet: Multi-Granular Uncertainty Modeling for Efficient Hallucination Detection in LLM Question Answering
Large Language Models (LLMs) excel at question answering (QA) but often generate hallucinations, including factual errors or fabricated content. Detecting hallucinations from internal uncertainty signals is attractive due to its scalability and independence from external resources. Existing methods often aim to accurately capture a single type of uncertainty while overlooking the complementarity among different sources, particularly between token-level probability uncertainty and the uncertainty conveyed by internal semantic representations, which provide complementary views on model reliability. We present \textbf{HaluNet}, a lightweight and trainable neural framework that integrates multi granular token level uncertainties by combining semantic embeddings with probabilistic confidence and distributional uncertainty. Its multi branch architecture adaptively fuses what the model knows with the uncertainty expressed in its outputs, enabling efficient one pass hallucination detection. Experiments on SQuAD, TriviaQA, and Natural Questions show that HaluNet delivers strong detection performance and favorable computational efficiency, with or without access to context, highlighting its potential for real time hallucination detection in LLM based QA systems.
Open AccessHaluNet: Multi-Granular Uncertainty Modeling for Efficient Hallucination Detection in LLM Question Answering
Large Language Models (LLMs) excel at question answering (QA) but often generate hallucinations, including factual errors or fabricated content. Detecting hallucinations from internal uncertainty signals is attractive due to its scalability and independence from external resources. Existing methods often aim to accurately capture a single type of uncertainty while overlooking the complementarity among different sources, particularly between token-level probability uncertainty and the uncertainty conveyed by internal semantic representations, which provide complementary views on model reliability. We present \textbf{HaluNet}, a lightweight and trainable neural framework that integrates multi granular token level uncertainties by combining semantic embeddings with probabilistic confidence and distributional uncertainty. Its multi branch architecture adaptively fuses what the model knows with the uncertainty expressed in its outputs, enabling efficient one pass hallucination detection. Experiments on SQuAD, TriviaQA, and Natural Questions show that HaluNet delivers strong detection performance and favorable computational efficiency, with or without access to context, highlighting its potential for real time hallucination detection in LLM based QA systems.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 9, 8222-8230
T-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction
Aspect sentiment triplet extraction (ASTE) aims to extract triplets composed of aspect terms, opinion terms, and sentiment polarities from given sentences. The table tagging method is a popular approach to addressing this task, which encodes a sentence into a 2-dimensional table, allowing for the tagging of relations between any two words. Previous efforts have focused on designing various downstream relation learning modules to better capture interactions between tokens in the table, revealing that a stronger capability in relation capture can lead to greater improvements in the model. Motivated by this, we attempt to directly utilize transformer layers as downstream relation learning modules. Due to the powerful semantic modeling capability of transformers, it is foreseeable that this will lead to excellent improvement. However, owing to the quadratic relation between the length of the table and the length of the input sentence sequence, using transformers directly faces two challenges: overly long table sequences and unfair local attention interaction. To address these challenges, we propose a novel Table-Transformer (T-T) for the tagging-based ASTE method. Specifically, we introduce a stripe attention mechanism with a loop-shift strategy to tackle these challenges. The former modifies the global attention mechanism to only attend to a 2-dimensional local attention window, while the latter facilitates interaction between different attention windows. Extensive and comprehensive experiments demonstrate that the T-T, as a downstream relation learning module, achieves state-of-the-art performance with lower computational costs.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 9, 8222-8230
Open AccessT-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction
Aspect sentiment triplet extraction (ASTE) aims to extract triplets composed of aspect terms, opinion terms, and sentiment polarities from given sentences. The table tagging method is a popular approach to addressing this task, which encodes a sentence into a 2-dimensional table, allowing for the tagging of relations between any two words. Previous efforts have focused on designing various downstream relation learning modules to better capture interactions between tokens in the table, revealing that a stronger capability in relation capture can lead to greater improvements in the model. Motivated by this, we attempt to directly utilize transformer layers as downstream relation learning modules. Due to the powerful semantic modeling capability of transformers, it is foreseeable that this will lead to excellent improvement. However, owing to the quadratic relation between the length of the table and the length of the input sentence sequence, using transformers directly faces two challenges: overly long table sequences and unfair local attention interaction. To address these challenges, we propose a novel Table-Transformer (T-T) for the tagging-based ASTE method. Specifically, we introduce a stripe attention mechanism with a loop-shift strategy to tackle these challenges. The former modifies the global attention mechanism to only attend to a 2-dimensional local attention window, while the latter facilitates interaction between different attention windows. Extensive and comprehensive experiments demonstrate that the T-T, as a downstream relation learning module, achieves state-of-the-art performance with lower computational costs.
- 10 August 2025
- Published by Springer Nature
- p. 325-343
A Two-Step Data Augmentation Method for Cross-Lingual Sentiment Classification
- 10 August 2025
- Published by Springer Nature
- p. 325-343
A Two-Step Data Augmentation Method for Cross-Lingual Sentiment Classification
- Open Access
T-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction
Aspect sentiment triplet extraction (ASTE) aims to extract triplets composed of aspect terms, opinion terms, and sentiment polarities from given sentences. The table tagging method is a popular approach to addressing this task, which encodes a sentence into a 2-dimensional table, allowing for the tagging of relations between any two words. Previous efforts have focused on designing various downstream relation learning modules to better capture interactions between tokens in the table, revealing that a stronger capability to capture relations can lead to greater improvements in the model. Motivated by this, we attempt to directly utilize transformer layers as downstream relation learning modules. Due to the powerful semantic modeling capability of transformers, it is foreseeable that this will lead to excellent improvement. However, owing to the quadratic relation between the length of the table and the length of the input sentence sequence, using transformers directly faces two challenges: overly long table sequences and unfair local attention interaction. To address these challenges, we propose a novel Table-Transformer (T-T) for the tagging-based ASTE method. Specifically, we introduce a stripe attention mechanism with a loop-shift strategy to tackle these challenges. The former modifies the global attention mechanism to only attend to a 2-dimensional local attention window, while the latter facilitates interaction between different attention windows. Extensive and comprehensive experiments demonstrate that the T-T, as a downstream relation learning module, achieves state-of-the-art performance with lower computational costs.
Open AccessT-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction
Aspect sentiment triplet extraction (ASTE) aims to extract triplets composed of aspect terms, opinion terms, and sentiment polarities from given sentences. The table tagging method is a popular approach to addressing this task, which encodes a sentence into a 2-dimensional table, allowing for the tagging of relations between any two words. Previous efforts have focused on designing various downstream relation learning modules to better capture interactions between tokens in the table, revealing that a stronger capability to capture relations can lead to greater improvements in the model. Motivated by this, we attempt to directly utilize transformer layers as downstream relation learning modules. Due to the powerful semantic modeling capability of transformers, it is foreseeable that this will lead to excellent improvement. However, owing to the quadratic relation between the length of the table and the length of the input sentence sequence, using transformers directly faces two challenges: overly long table sequences and unfair local attention interaction. To address these challenges, we propose a novel Table-Transformer (T-T) for the tagging-based ASTE method. Specifically, we introduce a stripe attention mechanism with a loop-shift strategy to tackle these challenges. The former modifies the global attention mechanism to only attend to a 2-dimensional local attention window, while the latter facilitates interaction between different attention windows. Extensive and comprehensive experiments demonstrate that the T-T, as a downstream relation learning module, achieves state-of-the-art performance with lower computational costs.
- 29 June 2024
- Published by Springer Nature
- p. 438-452
Local Attention Augmentation for Chinese Spelling Correction
- 29 June 2024
- Published by Springer Nature
- p. 438-452
Local Attention Augmentation for Chinese Spelling Correction
- 14 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (12) , 12295-12309
Learning Discriminative Text Representation for Streaming Social Event Detection
Event detection on social platforms can help people perceive essential events and make actionable decisions. Existing document-pivot streaming social event detection methods generally embed documents and perform text clustering. They face the challenges of constantly changing context and unknown event categories and struggle by designing compound text representation methods and various similarity measures. However, phased, well-designed methods are excessively fragile and unable to utilize the potential of text representations fully. Meanwhile, their complex threshold settings result in clustering-based event detection suffering the pain of ever-changing environments. We propose a text representation learning method namely Text Sim ilarity C ontrastive L earning N eural N etwork (Text-SimCLNN) to tackle these challenges. Text-SimCLNN uses smaller parts to learn the similarity probability of text pairs from semantic and structural perspectives, effectively bridging the gap between text representation learning and similarity measure in streaming event detection. Event discovery and merging in streams can be easily performed based on the learned representations, and we use various techniques to speed up such processes. Furthermore, we introduce an online update mechanism that uses heterogeneous graphs to generate high-quality samples to enable stable and reliable inductive learning. Extensive experiments on two real-world datasets demonstrate that our method far exceeds state-of-the-art (SOTA).
- 14 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (12) , 12295-12309
Learning Discriminative Text Representation for Streaming Social Event Detection
Event detection on social platforms can help people perceive essential events and make actionable decisions. Existing document-pivot streaming social event detection methods generally embed documents and perform text clustering. They face the challenges of constantly changing context and unknown event categories and struggle by designing compound text representation methods and various similarity measures. However, phased, well-designed methods are excessively fragile and unable to utilize the potential of text representations fully. Meanwhile, their complex threshold settings result in clustering-based event detection suffering the pain of ever-changing environments. We propose a text representation learning method namely Text Sim ilarity C ontrastive L earning N eural N etwork (Text-SimCLNN) to tackle these challenges. Text-SimCLNN uses smaller parts to learn the similarity probability of text pairs from semantic and structural perspectives, effectively bridging the gap between text representation learning and similarity measure in streaming event detection. Event discovery and merging in streams can be easily performed based on the learned representations, and we use various techniques to speed up such processes. Furthermore, we introduce an online update mechanism that uses heterogeneous graphs to generate high-quality samples to enable stable and reliable inductive learning. Extensive experiments on two real-world datasets demonstrate that our method far exceeds state-of-the-art (SOTA).