Papers by Haotian Xu

14 papers
Too Long, Do Re-weighting for Efficient LLM Reasoning Compression (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques.
Approach: They propose a method that uses Extended Chain-of-Thought (EFT) to reduce the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
Outcome: The proposed method reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning.
MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have improved generation and reasoning capabilities compared to traditional BERT-sized models due to massive number of parameters and extensive pre-training on vast textual corpora.
Approach: They propose a unified post-hoc adapter for test-time adaptation of large language models . they propose to fine-tune only a small BERT-sized adapter to rank candidate LLMs .
Outcome: The proposed adapter improves performance on four biomedical tasks without requiring computational resources or sharing data with third parties.
Triple-Hybrid Energy-based Model Makes Better Calibrated Natural Language Understanding Models (2023.eacl-main)

Copied to clipboard

Challenge: In-distribution (ID) miscalibration and out-of-difference (OOD) detection are main concerns for pre-trained language models.
Approach: They propose a triple-hybrid EBM which combines the benefits of classifier, conditional generative model and marginal generative models altogether.
Outcome: The proposed model outperforms previous methods in terms of ID calibration and OOD detection by a large margin while maintaining competitive accuracy.
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Copied to clipboard

Challenge: Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach: They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome: The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.
CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on indoor or street settings, overlooking challenges of open-ended urban spaces.
Approach: They propose a benchmark to probe cross-view spatial reasoning capabilities of current VLMs in urban settings.
Outcome: The citycube benchmark examines the performance of current vision-language models in urban environments.
RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for static knowledge graph embedding (SKGE) ignore the continuity of states of TKGs in time evolution.
Approach: They propose a Recursive Temporal Fact Embedding framework to transplant SKGE models to TKGs and enhance the performance of existing TKGE models.
Outcome: The proposed framework can be used to transplant SKGE models to TKGs and improve existing models for TKG completion.
Shuttle Between Symbolic Instructions and Neural Parameters of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Despite their distinct external representations, a deeper analysis reveals their intrinsic nature: instructions serve as a natural language compression devised by humans for data governing specific mapping patterns, whereas parameters act as 'neuro compression' of the same task data.
Approach: They propose a neural network framework to model and learn the bi-directional mappings between instructions and parameters of large language models by evaluating it on the tasks of instruction deduction and induction.
Outcome: The proposed framework can map one of the instructions/parameters to the other by evaluating it on the tasks of instruction deduction and induction.
EMONA: Event-level Moral Opinions in News Articles (2024.naacl-long)

Copied to clipboard

Challenge: Recent work on news articles has focused on social media short texts, but little has explored moral sentiment within news articles.
Approach: They propose to extract event-level moral opinions from news articles using a new dataset . they use annotated event-based moral opinions to analyze news articles .
Outcome: The proposed dataset consists of 400 news articles containing over 10k sentences and 45k events, among which 9,613 events received moral foundation labels.
ItD: Large Language Models Can Teach Themselves Induction through Deduction (2024.acl-long)

Copied to clipboard

Challenge: Recent studies have shown that Large Language Models (LLMs) have limited ability to conduct induction.
Approach: They propose a framework to enable LLMs to teach themselves induction through deduction.
Outcome: The proposed framework improves performance on two induction benchmarks and shows that it can be used to teach induction through deduction.
Self-Knowledge Distillation for Knowledge Graph Embedding (2024.lrec-main)

Copied to clipboard

Challenge: Knowledge graph embedding (KGE) is an important task for many downstream applications.
Approach: They propose to use self-knowledge distillation to learn a low-dimensional model from a pre-trained high-dimensional one.
Outcome: The proposed model can improve model performance while maintaining lightweight structure.
Crossroads, Buildings and Neighborhoods: A Dataset for Fine-grained Location Recognition (2022.naacl-main)

Copied to clipboard

Challenge: Named Entity Recognition (NER) datasets annotate coarse-grained entities such as a continent, a country, or a city.
Approach: They propose a dataset HarveyNER with fine-grained locations annotated in tweets that characterizes many complex and long location mentions in informal descriptions.
Outcome: The proposed dataset outperforms existing systems on hard cases and improves on the heuristic curricula.
Natural Language Processing in Support of Evidence-based Medicine: A Scoping Review (2025.findings-acl)

Copied to clipboard

Challenge: Evidence-based medicine (EBM) is at the forefront of modern healthcare, emphasizing the use of the best available scientific evidence to guide clinical decisions.
Approach: They propose to investigate the use of Natural Language Processing (NLP) techniques to identify, appraise, synthesize, apply, and disseminate evidence in EBM.
Outcome: The proposed methods support the five fundamental steps of EBM—Ask, Acquire, Appraise, Apply, and Assess.
Causally Modeling the Linguistic and Social Factors that Predict Email Response (2025.naacl-long)

Copied to clipboard

Challenge: a key intent behind many emails is to get a reply from the recipient.
Approach: They propose to model the intents, expectations, and responsiveness in email exchanges by using a dataset containing 1800 emails annotated with nuanced types of intents and expectations.
Outcome: The proposed model is based on 1800 emails annotated with nuanced types of intents and expectations . it shows that social status, argumentation, and strength of social connection influence email response rates .
OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing RLHF frameworks face inference bottlenecks and complexity barriers restricting their accessibility for newcomers.
Approach: They propose an open-source RLHF framework that can be used to train large language models.
Outcome: The proposed framework achieves superior training efficiency with speedups ranging from 1.22 to 1.68 across different model sizes compared to state-of-the-art frameworks, while requiring significantly fewer lines of code for implementation.

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