Papers by Liqiang Xiao

12 papers
Learning What to Share: Leaky Multi-Task Network for Text Classification (C18-1)

Copied to clipboard

Challenge: Existing approaches to multi-task learning suffer from the interference between tasks because they lack selection mechanism for feature sharing.
Approach: They propose a multi-task convolutional neural network with the Leaky Unit which has memory and forgetting mechanism to filter the feature flows between tasks.
Outcome: The proposed model can filter feature flows between tasks and improve performance on five datasets.
Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks primarily evaluate planning and execution success, overlooking the self-reflective dimension of tool use.
Approach: They propose a benchmark to assess LLMs’ self-reflective reasoning in tool-augmented multi-turn dialogues.
Outcome: The proposed benchmark covers 10 domains with 88 distinct APIs and 968 annotated dialogues, systematically injecting diverse error types arising from both user and assistant behavior.
Gated Multi-Task Network for Text Classification (N18-2)

Copied to clipboard

Challenge: Existing approaches to multitask learning share the features without distinguishing the usefulness of the features, generating undesired interference between tasks.
Approach: They propose to introduce a gate mechanism into multi-task CNN and propose a new gated sharing unit which can filter the feature flows between tasks and greatly reduce the interference.
Outcome: The proposed approach can learn selection rules automatically and gain a great improvement over strong baselines.
MCapsNet: Capsule Network for Text with Multi-Task Learning (D18-1)

Copied to clipboard

Challenge: Multi-task learning has been frustrated by the interference among tasks.
Approach: They propose a capsule-based multi-task learning architecture which is unified, simple and effective.
Outcome: The proposed model can cluster features for each task in the network, which helps reduce the interference among tasks.
End-to-End Conversational Search for Online Shopping with Utterance Transfer (2021.emnlp-main)

Copied to clipboard

Challenge: a new study proposes a conversational search system that integrates product attributes and dialog with search . but it faces two real world challenges: imperfect product schema/knowledge and lack of training dialog data .
Approach: They propose an end-to-end conversational search system that integrates search with text . they propose an utterance transfer approach that generates dialogue utterations from other domains .
Outcome: The proposed system outperforms the best tested baseline in a conversational search dataset for online shopping.
Modeling Content Importance for Summarization with Pre-trained Language Models (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies on content importance do not consider semantics and context when evaluating importance.
Approach: They apply information theory to pre-trained language models to define the concept of importance from the perspective of information amount.
Outcome: Experiments on CNN/Daily Mail and New York Times show that the proposed model can model the importance of content better than previous methods based on F1 and ROUGE scores.
Exploring Logically Dependent Multi-task Learning with Causal Inference (2020.emnlp-main)

Copied to clipboard

Challenge: Hierarchical multi-task learning models can utilize task dependencies by stacking encoders and outperform democratic ones.
Approach: They propose a model that utilizes the labels of all lower-level tasks and a Gumbel sampling model to deal with cascading errors.
Outcome: The proposed model outperforms democratic models on six out of seven subtasks and achieves state-of-the-art on the two English and one Chinese datasets.
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding (2025.findings-acl)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) are limited by context length when processing long videos.
Approach: They propose a training-free method that flexibly reduces redundancy by allocating compression ratios among time and model layers with theoretical guarantees.
Outcome: Experiments on videoMME, MLVU, LongVideoBench, and LVBench show that AdaRETAKE outperforms existing methods by 2.3% and 2.8% for 7B and 72B models.
A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation (2020.coling-main)

Copied to clipboard

Challenge: Paraphrase generation is a longstanding problem in natural language processing (NLP) Neural network-based methods have shown great progress on paraphrase generation.
Approach: They propose a framework that integrates variational inference on a target-related latent variable to introduce the diversity.
Outcome: The proposed framework outperforms baseline models on the metrics based on n-gram matching and semantic similarity, and it can generate multiple different paraphrases by assembling different syntactic variables.
Multi-Task Label Embedding for Text Classification (D18-1)

Copied to clipboard

Challenge: Existing work treats labels of each task as independent and meaningless one-hot vectors, which cause a loss of potential label information.
Approach: They propose to combine multi-task learning with semantic vectors to convert labels into vectors . their results are based on extensive experiments on five benchmark datasets based in chinese .
Outcome: The proposed model can improve performance on five benchmark datasets on text classification tasks.
Diagnosing the First-Order Logical Reasoning Ability Through LogicNLI (2021.emnlp-main)

Copied to clipboard

Challenge: Existing studies have focused on diagnosing LMs' reasoning abilities in natural language understanding tasks.
Approach: They propose a diagnostic method for first-order logic reasoning with a proposed benchmark, LogicNLI.
Outcome: The proposed method disentangles the target FOL reasoning from commonsense inference and can be used to diagnose LMs from four perspectives: accuracy, robustness, generalization, and interpretability.
HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing studies have shown that high-quality video captions can improve MLLMs' performance on videos involving human actions.
Approach: They propose a data annotation pipeline to collect videos featuring clear human actions from the Internet and annotate them in a standardized caption format that uses human attributes to distinguish individuals.
Outcome: The proposed pipeline combines two datasets to evaluate human action understanding.

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