Papers by Shu-Tao Xia

9 papers
Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to detect large language models (LLMs) generated for plagiarism use paraphrases to rewrite them to evade detection.
Approach: They propose a training-free method that effectively fools text detectors using off-the-shelf LLMs by rewriting them to evade detection.
Outcome: The proposed method deceives text detectors using off-the-shelf LLMs by rewriting them to produce human-like sentences that are less discernible by detectors.
Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models (2026.acl-long)

Copied to clipboard

Challenge: Retrieval-augmented diffusion models (RDMs) have been developed to enhance performance with reduced parameters.
Approach: They propose to integrate retrieval-augmented diffusion models with Retrieval-augmented generation (RAG) that enhances performance with reduced parameters.
Outcome: The proposed framework achieves outstanding attack effects while maintaining benign utility.
Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Audio-Language Models (LALMs) have recently unlocked audio dialogue capabilities, enabling direct spoken exchanges with humans.
Approach: They propose to evaluate LALMs' open-ended audio dialogue ability in 3 general scenarios, 12 skills, 9 multilingual languages, and 4 categories of ambiguity handling.
Outcome: The proposed benchmark assesses the open-ended audio dialogue ability for LALMs in 3 general scenarios, 12 skills, 9 multilingual languages, and 4 categories of ambiguity handling.
When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Key-Value (KV) caching is widely used in large language models to enable long-context inference efficiently, yet its security implications remain underexplored.
Approach: They propose a history-aware, per-head feedback merging strategy that prevents safety degradation while maintaining efficiency.
Outcome: The proposed strategy prevents safety degradation while maintaining efficiency.
C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts (2026.findings-acl)

Copied to clipboard

Challenge: Recent efforts to develop algorithms for large language models (LLMs) have limited model diversity and data homogeneity in the Chinese corpora.
Approach: They propose a Chinese Real-prompt AI-generated text Detection benchmark that can be generalized to unseen LLMs and external Chinese datasets.
Outcome: The proposed benchmarks address critical gaps in model diversity, domain coverage, and prompt realism that have limited prior Chinese detection benchmarks.
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods neglect stylistic modeling and rely on static thresholds, which greatly limits the detection performance.
Approach: They propose a framework that enables stylistics-aware uncertainty quantification through conditional threshold estimation.
Outcome: The proposed framework achieves an average improvement 11.34% in detection performance compared to baselines.
Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation (2026.findings-acl)

Copied to clipboard

Challenge: 3D Vision-Language Models (VLMs) are critical cognitive backbone for spatial intelligence, but their reliance on autoregressive decoding introduces a fundamental vulnerability regarding inference efficiency.
Approach: They propose a framework that triggers computational and economic exhaustion in 3D-VLMs by injecting imperceptible noise that forces the model into a state of pathological verbosity.
Outcome: The proposed framework amplifies output length and energy consumption by up to 6.45, demonstrating a potent capability to drain system resources.
From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing multimodal large language models struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency.
Approach: They propose a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory that structures memory hierarchically into a *Sensory Buffer*, *Episodic Stream*, and *Symbolic Schema*.
Outcome: The proposed architecture achieves state-of-the-art on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization.
Modeling Uncertainty in Composed Image Retrieval via Probabilistic Embeddings (2025.acl-long)

Copied to clipboard

Challenge: Composed Image Retrieval (CIR) combines text and reference images to search for images . metric learning methods that focus on point embeddings fail to capture uncertainty in input data .
Approach: They propose a framework that captures uncertainty in images and queries by Gaussian distributions in latent space rather than fixed points.
Outcome: Experiments show that the proposed framework quantifies quality and semantic uncertainties . it can handle polysemy and ambiguity in search intentions, authors say .

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