Papers by Xiaoming Li

16 papers
FISTAPruner: Layer-wise Post-training Pruning for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing pruning methods require inefficient retraining for billion-scale LLMs or rely on heuristicically designed metrics to determine pruning masks, leading to performance degradation.
Approach: They propose a convex optimization model that induces sparsity in large language models by leveraging FISTA.
Outcome: The proposed method can remove 50% of model parameters while retaining 98.6% and 95.6% of the zero-shot performance.
Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation (2021.acl-long)

Copied to clipboard

Challenge: Existing methods require to learn to adapt the target model by exploiting the source data and sharing the network architecture across domains.
Approach: They propose a framework that allows to transfer the knowledge of source domain to the unlabeled target domain without using source data.
Outcome: The proposed framework matches distributions between a trained source model and a set of target data and achieves superior performance on cross-domain text classification.
Hyperbolic Graph Neural Network for Temporal Knowledge Graph Completion (2024.lrec-main)

Copied to clipboard

Challenge: Existing knowledge graph models are inefficient at capturing complex temporal dynamics and hierarchical relations within TKGs.
Approach: They propose to use hyperbolic geometry to effectively model temporal knowledge graphs . they use the hyperbolical gated Graph Neural Network and the hyperbipolar convolutional neural network .
Outcome: The proposed model achieves state-of-the-art performance on four benchmark datasets . it is compared with previous models and is expected to be useful in real-world applications .
Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training (2025.acl-long)

Copied to clipboard

Challenge: Existing MGT detectors are vulnerable to simple perturbations and adversarial attacks.
Approach: They propose an adversarial framework for training a robust machine-generated text detector called GREedy Adversary PromoTed DefendER.
Outcome: The proposed framework reduces the Attack Success Rate (ASR) by 0.67% compared with SOTA defense methods.
Confidence Should Be Calibrated More Than One Turn Deep (2026.acl-long)

Copied to clipboard

Challenge: Existing work on confidence estimation and calibration focuses on single-turn settings . existing work on multi-turn calibration ignores the risks and potential of multi-turned conversations .
Approach: They propose a multi-turn calibration task that reframes calibration from a static property into a dynamic challenge central to reliable multi- turn conversations.
Outcome: The proposed model minimizes ECE@T and leverages ConfChat to improve confidence . the proposed model preserves and even enhances model performance in multi-turn interactions.
Keyphrase Generation with Correlation Constraints (D18-1)

Copied to clipboard

Challenge: Existing methods for keyphrase generation ignore correlation among keyphrases, resulting in duplication and coverage issues.
Approach: They propose a new sequence-to-sequence architecture for keyphrase generation that captures correlation among keyphrases by preceding phrases to eliminate duplicate phrases and improve result coherence.
Outcome: The proposed model outperforms the state-of-the-art method on benchmark datasets in terms of accuracy and diversity.
TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models (2026.findings-acl)

Copied to clipboard

Challenge: Large Reasoning Models suffer from high inference latency due to autoregressive reasoning . SpecReason adopts a polling-based design that repeatedly invokes the LRM for verification at every step .
Approach: They propose a trigger-based collaborative reasoning framework that delegates most reasoning to the SRM and activates LRM intervention only when necessary.
Outcome: The proposed framework reduces latency and API cost by 73.3% under edge–cloud conditions.
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression (2026.acl-long)

Copied to clipboard

Challenge: Existing work on reducing CoT generation in reasoning impairs the necessary information for deriving the correct answer.
Approach: They propose a reasoning paradigm that takes CoT as a part of context to simplify the reasoning task for Large Language Models (LLMs).
Outcome: The proposed framework reduces the generation length of LLMs, but its effectiveness hinges on the efficiency and reliability of the contextual CoT generation.
Medical Dialogue System: A Survey of Categories, Methods, Evaluation and Challenges (2024.findings-acl)

Copied to clipboard

Challenge: Existing medical dialogue systems have significant potential to simplify diagnostic procedure and reduce the cost of collecting information from patients.
Approach: They analyze 325 papers from well-known computer science, natural language processing conferences and journals to find out the major challenges of medical dialog systems.
Outcome: The proposed systems have been surveyed in the medical community but have not been evaluated from a technical perspective.
Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to detect MGT from human-written texts are inadequate . existing methods are fine-tuned and zero-shot metric-based, but they can be more accurate.
Approach: They propose a novel fine-tuned detector that can detect MGT from human-written texts by contrastive learning on selective perturbation.
Outcome: The proposed method outperforms the state-of-the-art by 1.20% on four public datasets.
Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS (2026.acl-long)

Copied to clipboard

Challenge: Existing tool attacks are limited by domain specificity or fixed and static templates.
Approach: They propose an attack-based memory-augmented reinforcement learning process that constructs a dynamic attack memory and employs deliberative reasoning to retrieve adversarial patterns.
Outcome: Evo-Attacker outperforms baselines in the long-horizon credit assignment challenge.
A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Inductive reasoning is an important task for large language models (LLMs).
Approach: They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation.
Outcome: The proposed method improves inductive reasoning in large language models.
Do Not Guess, Verify: Logic-Guided Adaptive Reasoning for Multimodal Misinformation Detection (2026.findings-acl)

Copied to clipboard

Challenge: Existing multimodal misinformation detection paradigms rely on passive aggregation of multimodal features and social signals.
Approach: They propose a verification-oriented framework that integrates large vision–language models into multimodal misinformation detection through explicit rationale-guided reasoning.
Outcome: The proposed framework outperforms state-of-the-art methods on multimodal misinformation detection benchmarks while significantly reducing computational cost.
LlmFixer: Fix the Helpfulness of Defensive Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Several defense strategies have been introduced to defend against jailbreak attacks, but these strategies weakened the usefulness of large language models.
Approach: They propose a framework that acts on large language models equipped with any defense strategy to recover their usefulness.
Outcome: The proposed framework can be used on large language models to recover their usefulness without updating the parameters of a defensive large language model.
StablePT : Towards Stable Prompting for Few-shot Learning via Input Separation (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on prompt tuning have shown that language models can be effective few-shot learners with prompting.
Approach: They propose to treat the hard prompt and soft prompt as separate inputs to mitigate noise brought by prompt initialization.
Outcome: Experimental results show that the proposed method outperforms state-of-the-art methods by 6.97% in accuracy and reduces the standard deviation by 1.92 on average.
TF-Mamba: Text-enhanced Fusion Mamba with Missing Modalities for Robust Multimodal Sentiment Analysis (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing Transformer-based methods with missing modalities are difficult to use and have quadratic complexity.
Approach: They propose a text-enhanced Fusion Mamba framework for robust MSA with missing modalities . a Text-aware Modality Enhancement module aligns and enriches non-text modality while reconstructing missing text semantics.
Outcome: The proposed method is efficient under missing modalities and can be used in long-range modeling and multimodal fusion scenarios.

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