Papers by Haotian Ma
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. |
How Transliterations Improve Crosslingual Alignment (2025.coling-main)
Copied to clipboard
Yihong Liu, Mingyang Wang, Amir Hossein Kargaran, Ayyoob ImaniGooghari, Orgest Xhelili, Haotian Ye, Chunlan Ma, François Yvon, Hinrich Schütze
| Challenge: | Recent studies show that post-aligning multilingual pretrained language models improve crosslingual alignment, but it is unclear how and why this is achieved. |
| Approach: | They propose to explicitly evaluate crosslingual alignment by adding transliterations to models using original and transliterated data. |
| Outcome: | The proposed approach improves crosslingual alignment even for random sentences. |
GAP: a Global Adaptive Pruning Method for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing structured pruning methods employ uniform compression rates across network layers, neglecting the varying importance of different network depths. |
| Approach: | They propose a pruning framework that minimizes global capability loss by layer-adaptive pruning rates. |
| Outcome: | The proposed approach achieves comparable performance with state-of-the-art methods at high pruning rates and shows significant advantages at low pruning rates. |
TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data (2025.coling-main)
Copied to clipboard
| Challenge: | Existing mPLMs that handle non-transliterated data are not sufficient to train crosslingual models. |
| Approach: | They propose a framework to transliterate related languages into a common script by exploiting existing mPLMs and their tokenizer without any training. |
| Outcome: | The proposed framework can create strong baselines for data that is transliterated into a common script by exploiting an existing mPLM and its tokenizer without any training. |
Taxi1500: A Dataset for Multilingual Text Classification in 1500 Languages (2025.naacl-short)
Copied to clipboard
| Challenge: | a large-scale text classification dataset encompassing 1504 languages is needed to address this gap . low-resource languages are often overlooked due to the scarcity of evaluation datasets. |
| Approach: | They propose to use translations of the Bible to construct a large-scale text classification dataset that covers 1504 languages and annotate them using crowdsourcing. |
| Outcome: | The proposed dataset covers 1504 languages and is available to the public. |
TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | The world’s more than 7000 languages are written in at least 293 scripts, which poses a difficulty for multilingual pretrained language models in learning crosslingual knowledge through lexical overlap. |
| Approach: | They propose a framework that optimizes the Transliteration Contrastive Modeling objective to fine-tune an mPLM by contrasting sentences in its training data and transliterations in a unified script. |
| Outcome: | The proposed model outperforms Glot500-m on zero-shot crosslingual transfer tasks while retaining uniformity across scripts. |
ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction (2026.findings-acl)
Copied to clipboard
Zichun Guo, Yuling Shi, Wenhao Zeng, Chao Hu, Haotian Lin, Terry Yue Zhuo, Jiawei Chen, Xiaodong Gu, Wenping Ma
| Challenge: | Empirical evaluations on state-of-the-art MLLMs reveal a significant performance gap . ML models lack the fine-grained cross-modal reasoning required to bridge visual discontinuities. |
| Approach: | They propose a benchmark that renders fragmented documents directly from Markdown to facilitate evaluation of VRDU tasks. |
| Outcome: | The proposed benchmark renders fragmented documents directly from Markdown. |
LangSAMP: Language-Script Aware Multilingual Pretraining (2025.acl-long)
Copied to clipboard
| Challenge: | Recent multilingual pretrained language models often avoid using language embeddings, which places a significant burden on token representations to encode all language-specific information. |
| Approach: | They propose a method that incorporates both language and script embeddings into the output of Transformer blocks before passing the final representations to the language modeling head for prediction. |
| Outcome: | The proposed method outperforms the baseline model in zero-shot crosslingual transfer across diverse downstream tasks. |
Conflict-Aware Memory for Embodied Agents: Enhancing Vector Data Quality via Detection Rules (2026.acl-long)
Copied to clipboard
| Challenge: | Embodied agents have successfully leveraged large language models (LLMs) to better transform human instructions and images into executable task plans. |
| Approach: | They propose Conflict Detection Rules to identify and manage data quality issues in vector knowledge bases and correct the index structure. |
| Outcome: | Experimental results show that planners with Conflict Detection Rules exceed the basic LLM planner by 15.25% and 14.25% in grammatical accuracy (GA) and interpretation accuracy (IA) on average. |
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. |
DavIR: Data Selection via Implicit Reward for Large Language Models (2025.acl-long)
Copied to clipboard
Haotian Zhou, Tingkai Liu, Qianli Ma, Yufeng Zhang, Jianbo Yuan, Pengfei Liu, Yang You, Hongxia Yang
| Challenge: | 6% of Alpaca dataset selected with DavIR can steer both LLaMA and Gemma models to produce superior performance compared to the same models trained on the full 52K dataset. |
| Approach: | They propose a model-based data selection method for post-training Large Language Models . they generalize Reducible Holdout Loss to core-set selection problem of causal language modeling . |
| Outcome: | The proposed method can steer both LLaMA and Gemma models to superior performance compared to the same models trained on the full 52K dataset. |
Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research often overlooks the data quality issues within retrieval results, often caused by inaccurate existing vector-distance-based retrieval methods. |
| Approach: | They propose to use Context-Driven Index Trimming framework to capture and regulate consistency between retrieved contexts and modify indexes in the database. |
| Outcome: | Experiments show that the proposed framework can improve answer quality by 3.75% on open-domain question-answering tasks. |