Papers by Wentao Xu

11 papers
TC–RAG: Turing–Complete RAG’s Case study on Medical LLM Systems (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to RAG neglect system state variables, resulting in poor performance and erroneous knowledge accumulation.
Approach: They propose a framework that incorporates a Turing Complete System to manage state variables and manage retrieval halting.
Outcome: The proposed framework improves on seven real-world healthcare datasets and shows that it is more accurate than existing methods.
Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax (2026.findings-acl)

Copied to clipboard

Challenge: Extending large language models to low-resource languages often incurs an "alignment tax" token-level fine-tuning enforces token-level surface imitation on narrow and biased data distributions.
Approach: They propose a semantic-space alignment paradigm powered by group-level semantic rewards instead of likelihood maximization.
Outcome: The proposed model acquires low-resource capa- bilities while mitigating alignment tax on Tibetan–Chinese machine translation and Ti- betan headline generation.
ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training (2024.acl-long)

Copied to clipboard

Challenge: Experimental results demonstrate that ProtLLM achieves superior performance against protein-specialized baselines on protein-centric tasks and induces zero-shot and in-context learning capabilities on protein language tasks.
Approach: They propose a cross-modal large language model (LLM) that can handle protein-centric and protein-language tasks by using a dynamic protein mounting mechanism.
Outcome: The proposed model can predict proteins from a vast pool of candidates and can also predict natural language and biological papers.
Taming LLMs with Gradient Grouping (2025.acl-long)

Copied to clipboard

Challenge: a new study presents scaling with gradient grouping (SGG) the adaptive learning rate scaling approach is based on per-parameter statistics, which incurs memory overhead.
Approach: They propose an optimizer wrapper that improves adaptive learning rate estimation by dynamic grouping and group-specific scaling.
Outcome: The proposed algorithm improves learning rate estimation on diverse models with different model sizes and batch sizes.
KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings (2022.coling-1)

Copied to clipboard

Challenge: Existing knowledge graph embedding methods ignore semantic similarity between related entities and entity-relation couples in different triples .
Approach: They propose a contrastive learning framework for tensor decomposition based (TDB) KGE that can shorten the semantic distance of related entities and entity-relation couples in different triples and thus improve the performance of KGE.
Outcome: The proposed method achieves 51.2% MRR, 46.8% Hits@1 on three standard KGE datasets, 37.8% MRR and 28.6% Hits @1 on FB15k-237 datasets and 59.1% MRR .
RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for large language models focus on simple, flat table structures.
Approach: They propose a benchmark to evaluate the performance of both Large Language Models and Multimodal LLMs across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.
Outcome: The proposed benchmark evaluates the performance of LLMs and Multimodal LLM models across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.
Data-Centric Perspectives on Agentic Retrieval-Augmented Generation: A Survey (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel at natural language understanding and generation, yet rely on static pre-training data.
Approach: They propose to augment Large Language Models with external retrieval to ground model outputs . traditional RAG is constrained by a fixed retrieve-then-generate routine . authors aim to guide creation of high-quality datasets for next generation of adaptive LLM agents .
Outcome: The proposed model can decompose tasks, issue exploratory queries, and refine evidence through iterative retrieval.
SEEK: Segmented Embedding of Knowledge Graphs (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for knowledge graph embedding can not make a proper trade-off between the model complexity and the model expressiveness, which makes them far from satisfactory.
Approach: They propose a lightweight modeling framework that can achieve highly competitive relational expressiveness without increasing the model complexity.
Outcome: The proposed framework can achieve highly competitive relational expressiveness without increasing model complexity.
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for unsupervised text style transfer lack parallel data and difficulties in content preservation.
Approach: They propose a neural approach to unsupervised text style transfer using non-parallel data.
Outcome: The proposed approach can be trained end-to-end on two widely-used public datasets.
Data-to-Text Generation with Style Imitation (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles.
Approach: They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach .
Outcome: The proposed approach achieves stronger performance than a range of comparison methods.

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