Papers by Haotian Xie

5 papers
FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing models generate explanations that appear coherent while containing unfaithful intermediate steps.
Approach: They propose a causality-inspired framework for evaluating CoT quality using controlled perturbations as an instrumental signal to separate genuine step-to-step dependence from bias-driven artifacts.
Outcome: Experiments on GSM8K, MATH, and CommonsenseQA show that FACT-E improves reasoning-trajectory selection and yields stronger in-context learning exemplars.
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.
Reasoning under Uncertainty: Efficient LLM Inference via Unsupervised Confidence Dilution and Convergent Adaptive Sampling (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models suffer from overconfidence and computational inefficiency due to fixed computation budgets and miscalibrated confidence estimates.
Approach: They propose a framework for computationally efficient, trustworthy reasoning under uncertainty using Diversity-Aware Self-Signal Dilution and Convergent Adaptive Weighted Sampling techniques.
Outcome: The proposed framework reduces inference cost by 70% while maintaining accuracy levels while reducing inference costs.
Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks measure ToM capability improvement through story-reading, multiple-choice questions from a third-person perspective, while ignoring the first-person, dynamic nature of human-AI interactions.
Approach: They propose a new paradigm of interactive ToM evaluation with both perspective and metric shifts.
Outcome: The proposed approach improves the performance of four representative LLM enhancement techniques using real-world datasets and a user study.
CoAlign: Uncertainty Calibration of LLM for Geospatial Repartition (2025.acl-industry)

Copied to clipboard

Challenge: Existing methods to optimize geospatial repartition rely on manual adjustments by experts or algorithmic optimization using limited offline operational metrics.
Approach: They propose a framework that calibrates LLM uncertainty to enable robust geospatial repartition by integrating historical data with LLM-generated candidates.
Outcome: The proposed framework calibrates LLM uncertainty to enable robust geospatial repartition by integrating historical data with LLM-generated candidates.

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