Papers by Ting Hua

14 papers
Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage (2026.findings-acl)

Copied to clipboard

Challenge: Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency.
Approach: They propose an algorithm that detects threshold where information loss exceeds information gain during sparse decoding to reduce token consumption by up to 90% and a marginal accuracy degradation of less than 2%.
Outcome: The proposed algorithm reduces token consumption by 90% with a marginal accuracy degradation of less than 2% across reasoning-intensive benchmarks.
SMART: Evaluating LLMs’ Mathematical Reasoning via a Human Cognitive Process-Inspired Benchmark (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluation methods focus on the final answer or on the intermediate reasoning steps, overlooking its inherently multi-stage and multi-dimensional nature.
Approach: They propose a benchmark that decomposes mathematical problem-solving into four cognitive dimensions and introduces dimension-specific tasks to measure their cognitive processes.
Outcome: The proposed model decomposes mathematical problem-solving into four cognitive dimensions and introduces dimension-specific tasks to measure their cognitive processes.
Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation (2020.acl-main)

Copied to clipboard

Challenge: Existing word-level policy models that learn dialog policy and language generation from dialog corpora often lead to degeneration issues where the utterances become ungrammatical or repetitive.
Approach: They propose to represent prior dialog transitions as a graph and learn a CG grounded dialog policy that can foster a more coherent and controllable dialog.
Outcome: The proposed framework is able to learn dialog policy in open-domain multi-turn conversation.
Adaptive Rank Selections for Low-Rank Approximation of Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Singular Value Decomposition (SVD) or its weighted variants has progressed in compressing language models.
Approach: They propose a binary masking mechanism for optimizing the number of ranks in a differentiable framework.
Outcome: The proposed algorithm achieves much better accuracy than previous SVD and its weighted variants.
DuReadervis: A Chinese Dataset for Open-domain Document Visual Question Answering (2022.findings-acl)

Copied to clipboard

Challenge: Open-domain question answering is a task that requires answering questions based on a collection of document images.
Approach: They propose to use document images to answer questions using layouts and visual features instead of text.
Outcome: The proposed approach reduces human cost and improves scalability of QA systems by incorporating layouts and visual features.
HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches treat instruction-based text editing as a generic text generation problem. Existing methods either over-edit or fail to apply modifications consistently.
Approach: They propose a framework that processes each editing request to best align with it.
Outcome: The proposed framework achieves 9% improvement over the state-of-the-art model.
CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain? (2026.acl-long)

Copied to clipboard

Challenge: Existing multimodal large language models cannot generate executable procedures . authors propose a new benchmark to assess procedural competence in multimodal models .
Approach: They propose a new benchmark to assess procedural competence in multimodal large language models . they use a CrochetPARADE DSL representation to enable structural validation and functional evaluation .
Outcome: The proposed model enables structural validation and functional evaluation via execution.
Context Attribution with Multi-Armed Bandit Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to augmenting attribution with retrieval-augmented generation (RAG) focus on training models to explicitly cite context segments during generation, but their reliability remains unverifiable.
Approach: They propose a framework that formulates context attribution as a combinatorial multi-armed bandit problem by using Linear Thompson Sampling to efficiently identify the most influential context segments while minimizing the number of model queries.
Outcome: The proposed method reduces model queries by 30% while matching or exceeding the attribution quality of existing approaches.
Towards Conversational Recommendation over Multi-Type Dialogs (2020.acl-main)

Copied to clipboard

Challenge: In recent years, there has been a significant increase in the work of conversational recommendation due to the rise of voice-based bots.
Approach: They use a Chinese dialog dataset DuRecDial to study conversational recommendation in the context of multi-type dialogs where bots can proactively lead a conversation from a non-recommendation dialog to a recommendation dialog.
Outcome: The proposed dataset allows to investigate different parts of the overall problem, e.g., how to naturally lead a dialog, how interact with users for recommendation.
AgentDrug: Utilizing Large Language Models in an Agentic Workflow for Zero-Shot Molecular Optimization (2025.findings-emnlp)

Copied to clipboard

Challenge: Molecular optimization is a fundamental task in drug discovery.
Approach: They propose an agentic workflow that leverages LLMs in a structured refinement process to achieve significantly higher accuracy.
Outcome: The proposed workflow improves on single- and multi-property optimization tasks under loose and strict thresholds.
Numerical Optimizations for Weighted Low-rank Estimation on Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Singular value decomposition (SVD) is one of the most popular methods for estimating a target matrix with smaller matrices.
Approach: They propose a method that approximates a target matrix with smaller matrices by two smaller . they also propose metric to predict when the SVD may introduce a significant performance drop.
Outcome: The proposed method can perform better than current SOTA methods in compressing Transformer-based language models.
Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding (2021.naacl-main)

Copied to clipboard

Challenge: Existing continual learning approaches suffer from low accuracy and performance fluctuation when the distributions of old and new data are significantly different.
Approach: They propose a hyperparameter-free continual learning model for text data that can stably produce high performance under various environments.
Outcome: The proposed model outperforms the best state-of-the-art method by 20% in average accuracy and each component contributes effectively to overall performance.
Dynamic Low-rank Estimation for Transformer-based Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: RankDyna is a matrix decomposition method that can be used to compress Transformer-based language models.
Approach: They propose a matrix decomposition method that enables dynamic rank resource allocation . they say it can outperform current SOTA methods under various parameter budget levels .
Outcome: The proposed method outperforms current SOTA methods under various budget levels . the proposed method is more efficient with higher compression rates .
Process-Supervised Reinforcement Learning for Code Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing reinforcement learning strategies based on outcome supervision have shown effectiveness in code generation tasks, but their effectiveness in the field of code generation remains limited.
Approach: They propose a method that uses a teacher model to mutate and refactor statements and a compiler to automatically label them.
Outcome: The proposed method improves performance in complex code generation tasks.

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