Papers by Xue Tan

12 papers
Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models (2025.coling-industry)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit impressive performance across various domains but struggle with arithmetic reasoning tasks.
Approach: They propose a Teaching-Inspired Integrated Prompting Framework which emulates the instructional process of a teacher guiding students.
Outcome: The proposed framework improves reasoning accuracy on nine benchmarks.
DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling (2021.acl-long)

Copied to clipboard

Challenge: Existing systems for rap generation focus on rhyming lyrics but ignore rhythmic beats . rap lyrics need to be semantically meaningful and fashionable to convey interesting stories .
Approach: They develop a Transformer-based rap generation system that can model both rhymes and rhythms.
Outcome: The proposed system generates high-quality raps with rhymes and rhythms . it is based on a Transformer-based language model .
Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains (2025.findings-acl)

Copied to clipboard

Challenge: Existing Large Language Models (LLMs) generate brief answers without reasoning processes and explanations.
Approach: They propose supervised fine-tuning and tree search to enhance LLMs’ reasoning capabilities on domain tasks.
Outcome: The proposed model improves on stock investment recommendation and legal reasoning QA tasks.
PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption (2026.findings-acl)

Copied to clipboard

Challenge: Existing defense mechanisms lack theoretical robustness guarantees and perform unreliably when the LLM has limited knowledge of the retrieved content.
Approach: They propose a provably robust retrieval aggregation algorithm designed to defend against poisoning attacks on retrieved texts.
Outcome: Experiments show that PRA-RAG reduces the attack success rate to as low as 1% while maintaining an accuracy of 71%, significantly outperforming representative state-of-the-art (SOTA) methods.
V-Oracle: Making Progressive Reasoning in Deciphering Oracle Bones for You and Me (2025.acl-long)

Copied to clipboard

Challenge: Deciphering oracle bone scripts using AI technology is not an overnight task due to the evolution of written language over millennia.
Approach: They propose a framework that utilizes Large Multi-modal Models (LMMs) for interpreting Oracle Bone Script (OBS).
Outcome: The proposed framework provides quantitative analyses and superior deciphering capability.
PyramidCodec: Hierarchical Codec for Long-form Music Generation in Audio Domain (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to generate long music are inefficient and lack of structured representation.
Approach: They propose a hierarchical discrete representation of audio for long audio-domain music generation using residual vector quantization on different levels of features.
Outcome: The proposed method achieves competitive performance in terms of reconstruction quality and token per second (TPS) the proposed method facilitates training a language model that can generate well-structured long-form music for up to 3 minutes.
Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for detecting LLM-Generated text suffer from distribution misalignment and limited interpretability.
Approach: They propose a statistical framework utilizing supervised subspace learning to extract compact features and construct conditional semantic distributions based on syntactic structures.
Outcome: The proposed framework is superior in cross-domain, cross-model, and adversarial scenarios.
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (D19-1)

Copied to clipboard

Challenge: CoSQL is a corpus for building cross-domain, general-purpose database querying dialogue systems.
Approach: They present a corpus for building cross-domain, general-purpose database querying dialogue systems . they use a Wizard-of-Oz collection of 3k turns plus 10k+ annotated SQL queries .
Outcome: The proposed corpus is based on a Wizard-of-Oz dataset of 3k dialogues querying 200 complex DBs spanning 138 domains.
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored.
Approach: They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency .
Outcome: The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training.
RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis (2025.findings-emnlp)

Copied to clipboard

Challenge: Retrieval-Augmented Generation (RAG) enriches the input to LLMs by retrieving information from the relevant knowledge database.
Approach: They propose to use a knowledge database to enrich the input of LLMs by retrieving information from the relevant knowledge database.
Outcome: The proposed approach can achieve 98% true positive rate while maintaining a false positive rate close to 1%.
Joint Learning Event-Specific Probe and Argument Library with Differential Optimization for Document-Level Multi-Event Extraction (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods for document-level multi-event extraction neglect the fine-grained difference between events in multi-documents, which leads to event confusion and missing.
Approach: They propose an event-specific probe-based method to sniff multiple events by querying each corresponding argument library.
Outcome: The proposed method outperforms the state-of-the-art method in the recall of multi-events.
Auto-Evolve: Enhancing Large Language Model’s Performance via Self-Reasoning Framework (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in prompt engineering strategies rely on static seed reasoning modules to simulate human approach to problem-solving.
Approach: They propose a framework that enables LLMs to self-create dynamic reasoning modules and downstream action plan.
Outcome: The proposed framework outperforms existing prompting strategies on a BigBench-Hard dataset and improves performance by 2.8% over existing 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