Papers by Xiaoyuan Liu
Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to mitigating vision-knowledge conflict in Large Language Models (MLLMs) are not effective and can be further scaled. |
| Approach: | They propose a framework to generate inputs to simulate and evaluate vision-knowledge conflict in Multimodal Large Language Models (MLLMs) using original images and 1,122 high-quality question-answer pairs, they propose 'a diagnostic benchmark' |
| Outcome: | The proposed framework, benchmark, and analysis contribute to the understanding and mitigation of vision-knowledge conflicts in Multimodal Large Language Models (MLLMs). |
Can’t See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs (2025.acl-long)
Copied to clipboard
Wenxuan Wang, Xiaoyuan Liu, Kuiyi Gao, Jen-tse Huang, Youliang Yuan, Pinjia He, Shuai Wang, Zhaopeng Tu
| Challenge: | Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images. |
| Approach: | They propose a multimodal safety awareness benchmark to evaluate MLLMs across 29 safety scenarios with 1,500 carefully curated image-prompt pairs. |
| Outcome: | The proposed model is able to identify unsafe content and avoid over-sensitivity that can hinder helpfulness. |
Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment (2026.acl-long)
Copied to clipboard
Bryan Chen Zhengyu Tan, Zhengyuan Liu, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Roy Ka-Wei Lee
| Challenge: | Current alignment paradigms treat "human values" as a monolithic entity, ignoring the fact that many societies are a mosaic of diverse subgroups with distinct and sometimes conflicting values, preferences, and norms. |
| Approach: | They examine whether Large Language Models can emulate distinct cultural values of subgroups . they use a global value survey to examine the value landscape of a multicultural society . |
| Outcome: | The proposed model improves on unseen, out-of-distribution subgroups by 17.4% . the model widens the disparity between subgroup groups when measured by distance-aware metrics. |
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)
Copied to clipboard
Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen
| Challenge: | Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed . |
| Approach: | They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities. |
| Outcome: | The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech . |
MoLA: MoE LoRA with Layer-wise Expert Allocation (2025.findings-naacl)
Copied to clipboard
Chongyang Gao, Kezhen Chen, Jinmeng Rao, Ruibo Liu, Baochen Sun, Yawen Zhang, Daiyi Peng, Xiaoyuan Guo, Vs Subrahmanian
| Challenge: | Recent efforts to integrate low-rank adaptation (LoRA) with the Mixture-of-Experts (MoE) have achieved performance comparable to full-parameter fine-tuning by tuning much fewer parameters. |
| Approach: | They propose a parameter-efficient MoE method for low-rank adaptation with the Mixture-of-Experts (MoE) they use layers of LoRA experts to allocate more LoRA expert to middle layers . |
| Outcome: | The proposed method outperforms baseline models on six well-known NLP and commonsense QA benchmarks on LLAMA-2, Mistral, and Gemma. |
AI Sees Your Location—But With A Bias Toward The Wealthy World (2025.emnlp-main)
Copied to clipboard
| Challenge: | Visual Language Models (VLMs) have shown remarkable performance across various tasks, particularly in recognizing geographic information from images. |
| Approach: | They propose to use 1,200 images paired with detailed geographic metadata to evaluate VLMs' performance. |
| Outcome: | The models achieve 53.8% accuracy in city prediction, but exhibit significant biases in regional tasks. |
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards (2026.acl-long)
Copied to clipboard
Youliang Yuan, Qiuyang Mang, Jingbang Chen, Hong Wan, Xiaoyuan Liu, Junjielong Xu, Jen-tse Huang, Wenxuan Wang, Wenxiang Jiao, Pinjia He
| Challenge: | Existing models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability. |
| Approach: | They propose a Rubric Reward Model that rewards the entire reasoning trajectory against problem-specific rubrics. |
| Outcome: | The proposed model outperforms outcome-only supervision on four math benchmarks and boosts Verified Pass@1024 from 26.7% to 62.6% and reduces the incidence of Miracle Steps by 71%. |
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization (2026.acl-long)
Copied to clipboard
Shaohua Duan, Pengcheng Huang, Xinze Li, Zhenghao Liu, Xiaoyuan Yi, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu, Maosong Sun
| Challenge: | Recent studies have explored fine-tuning Large Language Models with synthetic data to enhance their long-context capabilities. |
| Approach: | They propose a framework that leverages a Multi-Armed Bandit rollout strategy to identify the most informative chunks from the given long context for sampling high-quality and diverse responses. |
| Outcome: | The proposed framework achieves 4% improvement on long-context reasoning benchmarks on Llama and Qwen. |
Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to steer LLMs towards human preference suffer from noisy positive-negative training pairs. |
| Approach: | They propose a distributional preference optimization method which maximizes discrepancy between dispreferred responses and generated non-negative ones. |
| Outcome: | The proposed method achieves comparable generation quality and surpasses the latest strong baselines in producing less harmful and more informative responses with better training stability and faster convergence. |
HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning (2025.findings-acl)
Copied to clipboard
Xiaoyuan Li, Moxin Li, Rui Men, Yichang Zhang, Keqin Bao, Wenjie Wang, Fuli Feng, Dayiheng Liu, Junyang Lin
| Challenge: | Existing studies show that large language models are robust in commonsense reasoning . however, some variations in questions can lead to incorrect responses . |
| Approach: | They propose a large-scale bilingual benchmark consisting of 11,200 cases . they conduct extensive experiments on 41 representative LLMs . |
| Outcome: | The proposed benchmark systematically evaluates the robustness of large language models in commonsense reasoning. |
MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation (2026.acl-long)
Copied to clipboard
Xiaoyuan Li, Keqin Bao, Yubo Ma, Moxin Li, Wenjie Wang, Rui Men, Yichang Zhang, Fuli Feng, Dayiheng Liu
| Challenge: | Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks. |
| Approach: | They propose to use a multi-turn reasoning evaluation framework to cover multi-turn interactions with the environments of large language models. |
| Outcome: | The proposed framework covers diverse reasoning capabilities, fine-grained difficulty granularity, and necessitates multi-turn interactions with the environments. |
Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing GEC models produce spurious corrections or fail to detect lots of errors. |
| Approach: | They propose a neural network for GEC quality estimation with multiple hypotheses . VERNet establishes interactions among hypothese based on reasoning graph . |
| Outcome: | The proposed model achieves state-of-the-art grammatical error detection performance and best quality estimation results on four GEC datasets. |
Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing researches in Scene Graph Generation (SGG) focus on refining model architectures that are trained from scratch with datasets like Visual Genome or Open Images. |
| Approach: | They propose to integrate pretrained Vision-language Models into SGG to improve representation by estimating the unattainable predicates distribution. |
| Outcome: | The proposed method significantly improves the performance of the debiased VLMs with SGG models. |
Sentence-aware Adversarial Meta-Learning for Few-Shot Text Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies fail to consider the importance of the semantic interaction between sentence features and neglect to enhance the generalization ability of the model to new tasks. |
| Approach: | They propose to integrate an adversarial network architecture into the meta-learning system and leverage cost-effective modules to build a few-shot classification framework called SaAML. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on four benchmark datasets. |
Pretrained Transformers Improve Out-of-Distribution Robustness (2020.acl-main)
Copied to clipboard
| Challenge: | Pretrained Transformers are more effective at detecting anomalous or OOD examples, while many previous models are frequently worse than chance. |
| Approach: | They construct a new robustness benchmark with real distribution shifts to measure out-of-distribution generalization for seven NLP datasets and compare them to previous models. |
| Outcome: | The proposed model generalizations for seven datasets show that pretrained Transformers are significantly less effective at detecting anomalous or OOD examples, while many previous models are often worse than chance. |