Papers by Shiyu Chang

28 papers
A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation (2025.naacl-long)

Copied to clipboard

Challenge: Current large language models (LLMs) produce factually incorrect statements .
Approach: They propose a probabilistic framework for LLM hallucination detection that generates a belief tree by expanding a statement into logically related claims and reasoning globally about the relationships between these claims.
Outcome: The proposed method improves on multiple hallucination detection benchmarks by 3%-9% over state-of-the-art models.
Self-Supervised Learning for Contextualized Extractive Summarization (P19-1)

Copied to clipboard

Challenge: Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss . previous work builds an end-to-end system to learn to choose sentences without explicitly modeling document context .
Approach: They propose three auxiliary pre-training tasks that learn to capture the document context in a self-supervised fashion.
Outcome: The proposed models outperform existing models on a CNN/DM dataset.
Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering (D19-58)

Copied to clipboard

Challenge: Existing work on open-domain multi-hop question answering relies on off-the-shelf information retrieval techniques to retrieve answer passages.
Approach: They propose a new subproblem for open-domain multi-hop question answering . they aim to recognize the anchor from a set of start passages with a reading comprehension model .
Outcome: The proposed method significantly improves the baseline method on the open-domain hotpotQA benchmark.
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers (P19-1)

Copied to clipboard

Challenge: Existing approaches to extract multiple relations from a paragraph require multiple passes over the paragraph.
Approach: They propose a method to extract multiple relations from a paragraph by encoding the paragraph only once.
Outcome: The proposed approach can perform state-of-the-art on the benchmark ACE 2005.
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control (D19-1)

Copied to clipboard

Challenge: Selective rationalization is a common mechanism to ensure that predictive models reveal how they use any available features.
Approach: They propose a co-operative method which uses introspection to explicitly predict and incorporate the outcome into the selection process.
Outcome: The proposed model maintains high predictive accuracy and leads to comprehensive rationales.
WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks (2026.findings-acl)

Copied to clipboard

Challenge: Large-language-model (LLM) agents are competent at straightforward web tasks, but struggle with complex tasks.
Approach: They propose a general framework that decomposes web tasks into three subtasks . they show that WebDART lifts end-to-end success rates by 13.7 percentage points .
Outcome: Evaluated on WebChoreArena, WebDART lifts success rates by 13.7 percentage points over previous state-of-the-art agents.
Out-of-Domain Detection for Low-Resource Text Classification Tasks (D19-1)

Copied to clipboard

Challenge: Existing methods for OOD detection and ID classification tasks require massive amounts of ID labeled data and no OOD labeles.
Approach: They propose to use OOD-resistant Prototypical Network to detect OOD cases with limited in-domain (ID) training data to solve this task.
Outcome: The proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task while maintaining a competitive performance on ID classification task.
Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to integrate external information into a given table neglect the structured nature of the table.
Approach: They propose a simple yet effective method to integrate external information into a given table by first building an augmenting table and then generating a SQL query over the two tables to answer the question.
Outcome: The proposed method outperforms strong baselines on three table QA benchmarks.
A Reinforcement Learning Framework for Robust and Secure LLM Watermarking (2026.eacl-long)

Copied to clipboard

Challenge: Existing watermarking algorithms rely on heuristic green/red token lists . however, these lists are inconsistent and can be compromised .
Approach: They propose a framework for robust and secure LLM watermarking using reinforcement learning.
Outcome: The proposed method achieves state-of-the-art trade-off across all criteria with notable improvements in resistance to spoofing attacks without degrading other criteria.
One-Shot Relational Learning for Knowledge Graphs (D18-1)

Copied to clipboard

Challenge: Existing studies on knowledge graph completion require a large number of positive examples for each relation, but long-tail relations are more common in KGs and those newly added relations do not have many known triples for training.
Approach: They propose a one-shot relational learning framework that utilizes the knowledge distilled by embedding models and learns a matching metric by considering both the learned embeddments and one-hop graph structures.
Outcome: The proposed framework improves on existing embedding models and eliminates the need for retraining when dealing with newly added relations.
Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2022.findings-acl)

Copied to clipboard

Challenge: Existing approaches to event extraction are limited to a set of pre-defined types.
Approach: They propose a natural language query framework that uses event types and argument roles to extract candidate triggers and arguments from input text.
Outcome: The proposed framework outperforms existing methods on zero-shot event extraction.
ADEPT-SQL: A High-performance Text-to-SQL Application for Real-World Enterprise-Level Databases (2025.acl-demo)

Copied to clipboard

Challenge: et al., 2017) address domain-specific knowledge barriers, schemas complexity, and computational costs of large LLMs.
Approach: They propose a domain-adapted Text2SQL system that addresses critical deployment challenges in professional fields.
Outcome: The proposed system achieves 97% execution accuracy on real-world databases . it is faster than existing systems and has a higher performance than existing ones.
Sentence Embedding Alignment for Lifelong Relation Extraction (N19-1)

Copied to clipboard

Challenge: Existing approaches to relation extraction require a fixed set of relations . Existing methods assume a closed set of relationships and perform once-and-for-all training on a set of datasets.
Approach: They propose to improve the stochastic gradient methods with a replay memory to alleviate the forgetting problem by anchoring the sentence embedding space.
Outcome: The proposed method outperforms state-of-the-art methods on multiple benchmarks.
Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader (P19-1)

Copied to clipboard

Challenge: Existing models that use incomplete knowledge bases and text data to answer open-domain questions are insufficient to cover full evidence.
Approach: They propose a model which learns to aggregate answer evidence from incomplete knowledge bases and text snippets.
Outcome: The proposed model improves on the widely-used KBQA benchmark WebQSP across settings with different extents of incompleteness.
Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to improve lifelong event detection performance are limited by the limited stored examples.
Approach: They propose to use Episodic Memory Prompts to explicitly retain the learned task-specific knowledge.
Outcome: The proposed method can be used to update a model with new event types while retaining the capability on previously learned types.
Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets (P19-1)

Copied to clipboard

Challenge: Natural Language Sentence Matching (NLSM) is a popular NLP task.
Approach: They propose to use QuoraQP to train and evaluate NLSM models using a selection bias framework.
Outcome: The proposed framework can improve generalization ability of trained models and give more trustworthy evaluation results for real-world adoptions.
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings (2022.naacl-main)

Copied to clipboard

Challenge: Recent work shows that finetuning pretrained models with contrastive learning makes it possible to learn good sentence embeddings without labeled data.
Approach: They propose an unsupervised contrastive learning framework for learning sentence embeddings . they use a masked language model to mask out the edited sentence .
Outcome: The proposed framework outperforms SimCSE on semantic textual similarity tasks by 2.3 absolute points.
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing (2024.naacl-short)

Copied to clipboard

Challenge: Existing adversarial attacks can cause LLMs to make wrong predictions on downstream tasks or generate harmful content misaligned with human values.
Approach: They propose to use randomized smoothing to add noise to the input and then make predictions based on these denoised versions.
Outcome: The proposed method surpasses existing methods in both empirical and certified robustness in defending against adversarial perturbations for both downstream tasks and human alignments (i.e., jailbreak attacks).
Complementary Evidence Identification in Open-Domain Question Answering (2021.eacl-main)

Copied to clipboard

Challenge: Existing approaches to QA that only measure the relevance between the question and each paragraph are not effective.
Approach: They propose a method that learns vector representations of passages and models the sufficiency and diversity within the selected set, in addition to the relevance between the question and passages.
Outcome: The proposed method significantly improves the accuracy of complementary evidence selection in open-domain question answering domain.
Context-Aware Conversation Thread Detection in Multi-Party Chat (D19-1)

Copied to clipboard

Challenge: In multi-party chat, it is common for multiple conversations to occur concurrently . a new model that automatically disentangles conversation threads is proposed .
Approach: They propose a Context-Aware Thread Detection model that automatically disentangles conversation threads in chat logs.
Outcome: The proposed model outperforms state-of-the-art models on four real-world chat logs.
Improving Reinforcement Learning Based Image Captioning with Natural Language Prior (D18-1)

Copied to clipboard

Challenge: Recent research shows that Reinforcement Learning (RL) approaches suffer from the exposure bias problem.
Approach: They propose a Reinforcement Learning (RL) based training framework that constrains the action space using an n-gram language prior.
Outcome: The proposed model is more human readable and graceful.
Revisiting Who’s Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective (2024.emnlp-main)

Copied to clipboard

Challenge: Existing and new datasets show that our approach achieves competitive performance in all of the criteria.
Approach: They propose a new task of LLM targeted unlearning where unlearning targets only the information about the unlearning target, rather than everything in the unlearned documents.
Outcome: The proposed method achieves competitive performance on existing and new datasets without optimizing for the aforementioned criteria.
Deriving Machine Attention from Human Rationales (D18-1)

Copied to clipboard

Challenge: Attention-based models are successful when trained on large amounts of data.
Approach: They propose an approach to map human-annotated rationales to high-performing attention and use this to guide models trained in low-resource scenarios.
Outcome: The proposed model yields over 15% error reduction on benchmark datasets.
A Co-Matching Model for Multi-choice Reading Comprehension (P18-2)

Copied to clipboard

Challenge: Existing approaches to machine comprehension are based on pairwise sequence matching, but this approach is not suitable for multi-choice reading comprehension since questions and answers are often equally important.
Approach: They propose a co-matching approach that models whether a passage can match both a question and a candidate answer using a dataset from Chinese exams.
Outcome: The proposed approach achieves state-of-the-art on the RACE dataset from Chinese middle and high school English examinations.
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning (2020.emnlp-main)

Copied to clipboard

Challenge: Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques.
Approach: They propose to re-formulate IF game solving as Multi-Passage Reading Comprehension tasks using context-query attention mechanisms and structured prediction to efficiently generate and evaluate action outputs.
Outcome: The proposed methods achieve high winning rates and low data requirements on the recent IF benchmark (Jericho)
Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing (N19-1)

Copied to clipboard

Challenge: Existing entity typing systems exploit type hierarchy provided by KB schema to model label correlations.
Approach: They propose a graph layer that encodes global label co-occurrence statistics and word-level similarities.
Outcome: The proposed model achieves a 15.3% relative F1 improvement on a large dataset with over 10,000 free-form types.
TWEETQA: A Social Media Focused Question Answering Dataset (P19-1)

Copied to clipboard

Challenge: Social media is becoming an important realtime information source, especially during natural disasters and emergencies.
Approach: They present a large-scale dataset for question answering over social media data . they gather tweets used by journalists and ask human annotators to write questions upon them .
Outcome: The proposed dataset shows that neural models that perform well on formal texts are limited in their performance . the proposed model is still lagging behind human performance with a large margin .
Diverse Few-Shot Text Classification with Multiple Metrics (N18-1)

Copied to clipboard

Challenge: Existing methods for few-shot learning are insufficient to capture task variations in natural language domains.
Approach: They propose an adaptive metric learning approach that automatically determines the best weighted combination from a set of metrics obtained from meta-training tasks for a newly seen few-shot task.
Outcome: The proposed method performs favorably against state-of-the-art few shot learning algorithms on real-world sentiment analysis and dialog intent classification datasets.

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