Papers by Xuelong Li

16 papers
Dual Prompt Tuning based Contrastive Learning for Hierarchical Text Classification (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods focus on hierarchy-aware text feature by exploiting explicit parent-child relationships, resulting in label confusion within each layer.
Approach: They propose a dual-prompt tuning method which emphasizes discrimination among peer labels by performing contrastive learning on each hierarchical layer.
Outcome: The proposed method outperforms existing methods on benchmark datasets and is available on github.
LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have a high vulnerability to jailbreak attacks that leverage crafted prompts to generate malicious outputs.
Approach: They propose to use large language models to test their security against jailbreak attacks that leverage crafted prompts to generate malicious outputs.
Outcome: The proposed model is based on 320 manually crafted malicious code generation requirements, covering 11 jailbreak methods and 29 code functionality categories.
Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization (2026.findings-acl)

Copied to clipboard

Challenge: Hallucinations in Large Language Models persist in critical domains where generated content diverges from contextual facts or logical constraints.
Approach: They propose to generate hallucinations as orthogonal noise relative to the semantic manifold of the residual stream.
Outcome: The proposed method achieves superior contextual faithfulness compared to state-of-the-art methods.
The Mark Fades: Adaptive Evolutionary Paraphrase-based Attack against LLM Watermarks (2026.findings-acl)

Copied to clipboard

Challenge: Existing paraphrase-based watermark removal methods struggle to balance efficacy with text quality.
Approach: They propose a training-free evolutionary framework that models watermark removal as a constrained multi-objective optimization problem by using a Pseudo-Log-Likelihood-guided mutation to precisely target and modify watermark-carrying tokens.
Outcome: The proposed method outperforms baseline methods on a Qwen3 series watermark scheme while maintaining high semantic fidelity.
Awakening Dormant Experts:Counterfactual Routing to Mitigate MoE Hallucinations (2026.acl-long)

Copied to clipboard

Challenge: Sparse Mixture-of-Experts models are vulnerable to hallucinations, authors say . static Top-k routing leaves "specialist experts" under-prioritized for specific tokens .
Approach: They propose a training-free inference framework to awaken dormant experts . they propose 'counterfactual routing' to shift computational resources from syntax-dominant to knowledge-intensive layers .
Outcome: Experiments show that CoR improves factual accuracy by 3.1% without increasing the inference budget.
Visual Attention Reasoning via Hierarchical Search and Self-Verification (2026.acl-long)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) often hallucinate due to fragile, linear reasoning and weak visual grounding.
Approach: They propose a framework that reformulates reasoning as a hierarchical search with self-verification and replaces linear Chain-of-Thought with a tree-search policy capable of backtracking to correct logical errors.
Outcome: The proposed framework outperforms state-of-the-art methods on hallucination and safety benchmarks.
Table-R1: Region-based Reinforcement Learning for Table Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Tables are a widely used data format that poses unique challenges for language models due to their structured row-column interactions.
Approach: They propose a region-based reinforcement learning approach that integrates region evidence into reasoning steps.
Outcome: The proposed method outperforms baseline models on three benchmark datasets and significantly reduces the reasoning token consumption by 67.5%.
D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for fine-tuned large language models fail on fine-scale datasets . large data scale amplifies delta parameter magnitude, singular values, and entropy, causing compression errors.
Approach: They propose a training- and data-free delta compression method that captures dominant delta structure and compensates residual low-rank approximation to recover fine-grained details from smaller residual error.
Outcome: The proposed method outperforms existing methods on large-scale datasets on dense and MoE architectures.
WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for large language models focus on webpage generation outcomes.
Approach: They propose a multi-view evaluation framework to evaluate MLLMs in four key areas: WebUI Perception, HTML Programming, WebUI-HTML Understanding, and WebUI to code.
Outcome: The proposed framework evaluates MLLMs in four key areas: WebUI Perception, HTML Programming, WebUI-HTML Understanding, and WebUI to code.
Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for grounding large language models suffer from inefficient querying . Existing approaches that rely on physical verification or self-reflection suffer from excessive querying.
Approach: They propose a framework that introduces Reinforced Advantage feedback for efficient self-refinement of plans.
Outcome: The proposed framework surpasses baselines in success rate and significantly decreases interaction steps of agents and query rounds of LLMs.
CEMT:Controllable Element-Oriented Machine Translation via Structured Linguistic Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models suffer from paraphrasing errors, omissions, or hallucinations when input contains translation-specific elements that require strict preservation or controlled transformation.
Approach: They propose a Controllable Element-Oriented Machine Translation framework that decomposes the translation process into a linguistically grounded analysis, strategy formulation, and final generation.
Outcome: The proposed framework improves on the WMT23/24 Chinese–English benchmarks while significantly reducing element-level constraint violations.
Logic-Regularized Verifier Elicits Reasoning from LLMs (2025.acl-long)

Copied to clipboard

Challenge: Typical verifiers require resource-intensive supervised dataset construction, which is costly and faces limitations in data diversity.
Approach: They propose an unsupervised verifier regularized by logical rules that uses internal activations and logical constraints on multiple reasoning paths.
Outcome: Experiments on 10 datasets show that the proposed verifier outperforms baselines and is comparable to the supervised verifier.
Search to Pass Messages for Temporal Knowledge Graph Completion (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent studies on missing facts in temporal knowledge graphs are based on hand-designed architectures and fail to explore the diverse topological and temporal properties of TKGs.
Approach: They propose to use neural architecture search to design a data-specific message passing architecture for TKG completion.
Outcome: The proposed architectures achieve the state-of-the-art performance on three benchmark datasets.
T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)

Copied to clipboard

Challenge: Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications.
Approach: They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning.
Outcome: The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation.
INT: Establishing Information Transfer for Multilingual Intent Detection and Slot Filling (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies struggle to achieve performance comparable to that on high-resource languages due to inherent linguistic diversity of multilingual SLU tasks.
Approach: They propose a multilingual information transfer network to solve these challenges . they propose to reformulate SF as a span prediction problem and introduce a slot-matching attention mechanism to achieve slot alignment across languages.
Outcome: The proposed model outperforms baseline models on the MASSIVE and MASSIV-UG datasets in overall accuracy across all languages.
Improve LLM-as-a-Judge Ability as a General Ability (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies focus on generative judges, but only on their judge ability.
Approach: They propose a method that leverages the generative and reasoning capabilities of large language models to evaluate LLM responses across diverse scenarios, providing accurate preference signals.
Outcome: The proposed model performs on RewardBench with only 2% to 40% of the data required by other training frameworks.

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