Papers by Tianyu Cao

21 papers
Enhancing Continual Relation Extraction via Classifier Decomposition (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies only adopt a vanilla strategy when learning representations of new relations . experimental results show that the importance of the first training stage to CRE models may be underestimated.
Approach: They propose a framework that splits the last FFN layer into separated previous and current classifiers to maintain previous knowledge and encourage model to learn more robust representations at this training stage.
Outcome: The proposed framework outperforms the state-of-the-art models on two benchmarks.
DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing work on question-answer extraction fails to integrate incomplete utterances from dialog context for composite QA retrieval.
Approach: They propose a task where questions and corresponding answers might be separated across different utterances.
Outcome: The proposed methods perform well on 5 customer service datasets and set a benchmark for N-to-N DialogQAE with utterance and session level evaluation metrics.
Large Language Models are not Fair Evaluators (2024.acl-long)

Copied to clipboard

Challenge: Existing evaluation frameworks that use large language models as referees are insufficient for accurately assessing their alignment with human intent.
Approach: They propose a calibration framework to address positional bias in large language models as evaluators by manually annotating the “win/tie/lose” outcomes of responses from ChatGPT and Vicuna-13B in the Vicun A Benchmark’s question prompt.
Outcome: The proposed framework alleviates evaluation bias, resulting in closer alignment with human judgments.
Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization (2023.findings-emnlp)

Copied to clipboard

Challenge: Pretrained language models can be fine-tuned on limited training data, which can overfit and thus diminish performance.
Approach: They propose a fine-tuning strategy that selectively updates model parameters using gradients from various sub-nets dynamically generated by dropout.
Outcome: The proposed method outperforms existing methods on the GLUE benchmark and exhibits excellent generalization ability and robustness for domain transfer, data imbalance, and low-resource scenarios.
Beyond Polarity: Continuous Affect-Enhanced Multimodal Aspect-Based Sentiment Classification (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for multimodal aspect-based sentiment classification exploit discrete polarity patterns and generic visual embeddings.
Approach: They propose a Valence–Arousal–Dominance(VAD)-Enhanced MABSC framework that integrates VAD signals into multimodal sentiment reasoning and learns emotion-sensitive image representations.
Outcome: The proposed framework brings VAD signals into multimodal sentiment reasoning and learns emotion-sensitive image representations.
IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web (2025.findings-acl)

Copied to clipboard

Challenge: Existing models have been introduced to improve image comprehension, but there is no robust benchmark for imagetoweb conversion.
Approach: They propose a benchmark to assess imagetoweb conversion proficiency of large multimodal models . they propose to measure layout information of web pages by parsing the Document Object Model tree .
Outcome: The proposed benchmark measures the layout information of web pages—i.e., the positional relationships between elements—which has been overlooked by prior work.
Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach: They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome: The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)
Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion (2023.acl-long)

Copied to clipboard

Challenge: Prior denoising methods suppress redundant and noisy information at risk of losing critical information.
Approach: They propose a denoising bottleneck fusion model for fine-grained video multimodal fusion . they employ a bottleneck mechanism to filter out noise and redundancy with a restrained receptive field .
Outcome: The proposed model improves on state-of-the-art video multimodal fusion benchmarks.
Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to predict missing facts in knowledge graphs are limited in language alignment . SS-AGA uses seed alignment as an edge type to fuses all KGs as a whole graph .
Approach: They propose a self-supervised adaptive graph alignment method that fuses all KGs as a whole graph by regarding alignment as 'a new edge type' they propose SS-AGA method that uses relation-aware attention weights to capture potential alignment pairs in a new paradigm.
Outcome: The proposed method can predict missing facts in a knowledge graph (KG) but language alignment is scarce and new alignment identification is noisy.
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated excellent performance in numerous tasks but the parameterized knowledge stored within LLMs may be incomplete and hard to incorporate up-to-date knowledge.
Approach: They propose a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model’s problem-solving capabilities.
Outcome: The proposed method outperforms existing benchmarks on GPT3.5, Llama2 and other large language models significantly enhancing factual reasoning capabilities and reducing hallucinations.
Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing studies attribute catastrophic forgetting to the corruption of the learned representations as new relations come . Continual relation extraction models suffer from catastrophic forgetting when learning new relations .
Approach: They propose to use adversarial class augmentation mechanism to learn more precise representations . they propose to train the model on a sequence of tasks where two new relations are discovered .
Outcome: The proposed model improves on two popular benchmarks.
HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification (2022.emnlp-main)

Copied to clipboard

Challenge: Hierarchical text classification (HTC) is a multi-label classification problem with a complex label hierarchy.
Approach: They propose a Hierarchy-aware Prompt Tuning method to handle HTC from a multi-label perspective using a dynamic virtual template and label words that take the form of soft prompts to fuse the label hierarchy knowledge.
Outcome: The proposed method achieves state-of-the-art performance on 3 popular HTC datasets and is adept at handling imbalance and low resource situations.
Hierarchical Curriculum Learning for AMR Parsing (2022.acl-short)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, but there is a gap between their flat training objective and the hierarchic structure, which limits the model generalization.
Approach: They propose a Hierarchical Curriculum Learning framework with Structure-level (SC) and Instance-level curricula (IC) that aims to translate sentences to semantic representation with a hierarchical structure.
Outcome: Experiments on AMR2.0, AMR3.0, structure-complex and out-of-distribution situations confirm the effectiveness of the proposed framework.
DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection (2022.findings-emnlp)

Copied to clipboard

Challenge: DialogUSR is a plug-in and domain-agnostic module that empowers multi-intent detection for chatbots . a single user query triggers inquiries on highspeed train ticket price and weather of destination.
Approach: They propose a dialog utterance splitting and reformulation task that splits multi-intent user query into multiple single-intention sub-queries and recovers all coreferred and omitted information in the sub-questions.
Outcome: The proposed model can be used to split multi-intent user queries into multiple sub-queries . it can be trained in two stages and perform in-depth analyses on the proposed models .
Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data (2021.acl-long)

Copied to clipboard

Challenge: Existing work focuses on learning deep NER models with weak supervision without any human annotation.
Approach: They propose a framework that can suppress the noise of the weak labels and fine-tune over the strongly labeled data.
Outcome: The proposed framework outperforms existing methods on Named Entity Recognition tasks with weak supervision and weakly labeled data.
MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal Supervision (2021.emnlp-main)

Copied to clipboard

Challenge: Sequence labeling aims to predict fine-grained sequences of labels for text, but lack of token-level annotated data hinders the effectiveness of supervised methods.
Approach: They propose a Meta Teacher-Student (MetaTS) Network to alleviate data scarcity by leveraging large multilingual unlabeled data.
Outcome: The proposed meta learning method alleviates data scarcity by leveraging large multilingual unlabeled data.
An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling (2022.naacl-main)

Copied to clipboard

Challenge: Existing approaches to tagging tasks are limited to predefined classes and require large-scale annotated data.
Approach: They propose an Enhanced Span-based Decomposition method for Few-Shot Sequence Labeling to generalize on emerging, resource-scare domains.
Outcome: The proposed method achieves state-of-the-art results on two popular FSSL benchmarks, FewNERD and SNIPS, and is more robust in noisy and nested tagging scenarios.
Do LLMs Encode Frame Semantics? Evidence from Frame Identification (2025.emnlp-main)

Copied to clipboard

Challenge: Using the FrameNet lexical resource, we evaluate large language models under prompt-based inference and observe that they can perform frame identification effectively even without explicit supervision.
Approach: They evaluate large language models under prompt-based inference and observe that they encode latent knowledge of frame semantics.
Outcome: The proposed model can generate coherent frame definitions while generalizing well to out-of-domain benchmarks.
FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery (2023.findings-acl)

Copied to clipboard

Challenge: Existing intention-based studies on recommendation tasks are limited and use models to implicitly model the intention memberships.
Approach: They propose a framework that leverages the generation power of large language models and human-in-the-loop annotation to semi-automatically construct the intention knowledge graph.
Outcome: The proposed framework can model e-commerce knowledge and have many potential applications.
Out of Style: RAG’s Fragility to Linguistic Variation (2026.eacl-long)

Copied to clipboard

Challenge: linguistic reformulations impact both retrieval and generation stages, leading to a relative performance drop of up to 40.41% for less formal queries and 38.86% for queries containing grammatical errors.
Approach: They evaluate two retrieval models and nine LLMs across four QA datasets and examine how linguistic reformulations impact RAG performance.
Outcome: The proposed models show that linguistic reformulations significantly impact both retrieval and generation stages, leading to a performance drop of up to 40.41% for less formal queries and 38.86% for queries containing grammatical errors.
DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade (2024.naacl-long)

Copied to clipboard

Challenge: Existing models for natural language understanding are based on a well-defined intent 1 ontology.
Approach: They propose to retrain the natural language understanding model as new data from real users are merged into existing data.
Outcome: The proposed model shows that the semantically entangled intents can be recognized with an automatic workflow.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations