Papers by Xiaoran Liu

10 papers
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs (2026.acl-long)

Copied to clipboard

Challenge: High-quality post-training data is the primary engine driving LLM capabilities . datasets are often treated as isolated artifacts, overlooking their true developmental context .
Approach: They propose a framework to reconstruct the evolutionary graph of dataset development using data lineage.
Outcome: The proposed framework characterizes domain-specific structural patterns in Math-oriented datasets and general-domain corpora.
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Copied to clipboard

Challenge: Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach: They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome: The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)

Copied to clipboard

Challenge: Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations .
Approach: They propose a framework to synthesize complex charts and reliable reasoning data from scratch.
Outcome: Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models .
Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge (2023.acl-long)

Copied to clipboard

Challenge: Active learning has been proposed to alleviate data acquisition challenges for rare-class tasks when the class label is very infrequent (e.g., 5% of samples).
Approach: They propose to use transformers to train models on closely related tasks and evaluate acquisition strategies, including a proposed probability-of-rare-class approach to dissonance detection.
Outcome: The proposed method improves model accuracy while iterative transfer-learning does not improve cold-start performance.
LongWanjuan: Towards Systematic Measurement for Long Text Quality (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing efforts to improve data quality have focused on deduplication and the evaluation of data diversity and difficulty.
Approach: They propose a set of metrics to evaluate the quality of long texts by evaluating three fundamental linguistic dimensions: coherence, cohesion, and complexity.
Outcome: The proposed model improves on long-text tasks with over 160B tokens and categorizes long texts into holistic, aggregated, and chaotic types.
Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to optimize LLM for long sequences for long documents are slow and consume memory.
Approach: They propose a method that starts with a small memory size and gradually increases it . they propose Decremental Chunk based on Incremental Memory (IMDC) which reduces chunk size while increasing memory size .
Outcome: The proposed method is faster (1.45x) and reduces GPU memory consumption by 23.3% compared to fixed-size memory.
LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessment (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) show promise in simulating complex scenarios.
Approach: They examine multiple LLMs to proactively estimate perceived earthquake impacts using multimodal datasets and multimodal imagery.
Outcome: The framework generates Modified Mercalli Intensity (MMI) predictions at zip code and county scales using multimodal datasets.
CoLLiE: Collaborative Training of Large Language Models in an Efficient Way (2023.emnlp-demo)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly pivotal in a wide range of tasks . however, the resources required for training these models necessitate efficient solutions .
Approach: They propose a library that facilitates collaborative training of large language models . they use 3D parallelism, parameter-efficient fine-tuning methods and optimizers .
Outcome: The proposed library has proven superior training efficiency in comparison with prevalent solutions in pre-training and fine-tuning scenarios.
StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Copied to clipboard

Challenge: Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach: They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome: The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.
Capturing Human Cognitive Styles with Language: Towards an Experimental Evaluation Paradigm (2025.naacl-short)

Copied to clipboard

Challenge: While NLP models often capture cognitive states via language, validity of predicted states is determined by comparing annotations created without access to the cognitive states of the authors.
Approach: They propose a framework for evaluating language-based cognitive style models against human behavior by using an experiment-based framework.
Outcome: The proposed framework shows that language features can predict participants’ decision style with moderate-to-high accuracy (AUC 0.8), demonstrating that cognitive style can be partly captured and revealed by discourse patterns.

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