Papers by Yuting Xu

10 papers
Pun2Pun: Benchmarking LLMs on Textual-Visual Chinese-English Pun Translation via Pragmatics Model and Linguistic Reasoning (2025.acl-srw)

Copied to clipboard

Challenge: Current approaches resort to suboptimal compromises and computational methods remain inadequate for translation.
Approach: They propose a Constant-Variable Optimization (CVO) model for translation strategy and an Ovl metric for translation quality assessment that adapts to Chinese and English.
Outcome: The proposed model improves performance on textual and visual puns while maintaining linguistic mechanisms and humorous effects.
AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: AC-EVAL is a benchmark designed to assess the advanced knowledge and reasoning capabilities of LLMs within the context of ancient Chinese.
Approach: They propose a benchmark to assess the advanced knowledge and reasoning capabilities of LLMs in ancient Chinese.
Outcome: AC-EVAL aims to assess the comprehension of ancient Chinese texts . the benchmark covers 13 tasks covering historical facts, geography, social customs, art, philosophy, classical poetry and prose.
DCP: Dual-Cue Pruning for Efficient Large Vision-Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing pruning methods for large vision language models use visual tokens to prune . existing methods fail to balance efficiency and semantic alignment due to large number of visual token.
Approach: They propose a cross-modal pruning framework that considers textual semantics and visual self-attention to combine them to achieve efficient inference acceleration.
Outcome: The proposed pruning framework can retain only 25% of the visual tokens, with a minimal performance degradation of only 0.063% on LLaVA-1.5-13B.
Sinkhorn Distance Minimization for Knowledge Distillation (2024.lrec-main)

Copied to clipboard

Challenge: Existing knowledge distillation methods investigate divergence measures but fail to deliver effective supervision when few distribution overlap exists between teacher and student.
Approach: They propose a knowledge distillation method that exploits the Sinkhorn distance to ensure a nuanced assessment of the disparity between teacher and student distributions.
Outcome: The proposed method outperforms state-of-the-art methods on all kinds of LLMs with encoder-only, encoder decoder, and decoded architectures.
S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency (2025.naacl-long)

Copied to clipboard

Challenge: Large language models exhibit limitations when handling complex mathematical reasoning and logical inference tasks.
Approach: They propose a sparsification strategy to reduce token costs within Multi-agent Debate (MAD) this strategy minimizes ineffective exchanges of information and unproductive discussions among agents .
Outcome: The proposed approach reduces token costs by up to 94.5% while maintaining performance degradation below 2.0%.
TEACH: A Contrastive Knowledge Adaptive Distillation Framework for Classical Chinese Understanding (2025.acl-long)

Copied to clipboard

Challenge: Traditional methods for processing classical Chinese segment language understanding into discrete tasks, which overlook crucial background information and reduce user engagement.
Approach: They propose a framework that integrates word sense disambiguation with sentence translation to minimize hallucinations and improve semantic analysis.
Outcome: The proposed framework integrates word sense disambiguation with sentence translation to minimize hallucinations and improve semantic analysis.
Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debate (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to evaluate large language models fail to address cultural bias in non-Western languages . Chinese prompting shifts bias toward East Asian perspectives rather than eliminating it, authors say .
Approach: They propose a Chinese–English bilingual benchmark and multi-agent vote frameworks that enable explicit "no bias" judgments.
Outcome: The proposed framework achieves 57.6% average No Bias Rate on Chinese-English benchmark and 86.0% on Arabic CAMeL benchmark.
Exploring Question Guidance and Answer Calibration for Visually Grounded Video Question Answering (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for videoQA lack temporal localization labels, leading to inaccurate localization.
Approach: They propose a Question-Guided and Answer-Calibrated TRansformer which guides and calibrates localization using question and option texts without localization labels.
Outcome: The proposed model achieves comparable accuracy to large-scale pretrained models and leads in localization aspects.
H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving (2026.findings-acl)

Copied to clipboard

Challenge: Multi-tenant Model-as-a-Service (MaaS) workloads exhibit non-stationarity across multiple time scales . existing request schedulers often rely on a fixed policy that remains unchanged at runtime .
Approach: They propose a hierarchical multi-agent scheduler that operates in a layered closed loop . they propose to maintain 1.2–3.0 higher Goodput than SGLang and vLLM .
Outcome: Experiments show that H-MAS achieves 1.2–3.0 higher Goodput than SGLang and vLLM . it maintains more stable QoS under diverse request lengths and heterogeneous SLO targets .
Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks but their performance in complex logical reasoning tasks remains unsatisfactory.
Approach: They propose a propositional logic prompting method which generates expanded logical information descriptions and utilizes them as an additional augmentation to original contexts.
Outcome: Extensive experiments show that Logic-of-Thought boosts the performance of various prompting methods with a striking margin across five logical reasoning tasks.

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