Papers by Xiaohua Li

14 papers
Data Selection Curriculum for Abstractive Text Summarization (2023.findings-emnlp)

Copied to clipboard

Challenge: Abstractive Text Summarization (ATS) models are commonly trained using large-scale data that is randomly shuffled.
Approach: They propose a data selection curriculum scoring system that measures the learning difficulty of an ATS model and expected performance on an instance.
Outcome: The proposed system surpasses baselines on CNN/DailyMail dataset, utilizing 20% of available instances.
Contrastive Preference Learning for Neural Machine Translation (2024.findings-naacl)

Copied to clipboard

Challenge: Existing discrepancies between token-level objective and overall sequence-level quality of a model are causing exposure bias and other issues in NMT.
Approach: They propose a contrastive preference model that integrates an indicator function to fine-tune a pre-trained model in Neural Machine Translation.
Outcome: The proposed model outperforms the traditional Plackett-Luce model on three language pairs and also outperFORMs token-level and sequence-level baseline models.
Aligning Large Language Models with Human Preferences through Representation Engineering (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for achieving this alignment involve employing reinforcement learning from human feedback (RLHF) Existing approaches involve using RLHF to fine-tune LLMs based on human labels . however, RLRF is susceptible to instability during fine- tuning and presents challenges in implementation.
Approach: They propose to use reinforcement learning from human feedback to fine-tune large language models with human preferences to achieve precise control of model behavior.
Outcome: Experiments show that RAHF can be used to capture and manipulate representations to align with a broad spectrum of human preferences or values rather than being confined to a single concept or function.
MTLS: Making Texts into Linguistic Symbols (2024.emnlp-main)

Copied to clipboard

Challenge: In linguistics, all languages can be considered as symbolic systems . most work overlooks the properties of languages as symbol systems - aaron et al., 1989).
Approach: They propose a method to make texts into linguistic symbols to improve multilingual capability . they use a pre-training method to replace pre-trained language models with a vocabulary map .
Outcome: The proposed method improves multilingual capabilities on multilingual tasks using BERT and RoBERTa as the backbone.
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.
Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing (2025.findings-acl)

Copied to clipboard

Challenge: Role-playing Agents (RPAs) struggle to recognize and respond to hard queries that conflict with their role-play knowledge.
Approach: They propose a lightweight representation editing approach that conveniently shifts conflicting requests to the rejection region, thereby enhancing the model’s refusal accuracy.
Outcome: The proposed model improves RPAs’ refusal ability of conflicting requests while maintaining their general role-playing capabilities.
Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains.
Approach: They propose several strategies for deploying RAG that balance performance and efficiency.
Outcome: The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy.
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%.
HqeKV: Towards Hybrid Quantization and Eviction for KV Cache in Long-Context LLM Inference (2026.findings-acl)

Copied to clipboard

Challenge: autoregressive inference requires repeated computation across transformer layers.
Approach: They propose a hybrid compression framework built on both quantization and eviction . they propose varying importance metric and flexible conversion policies to reduce memory overhead .
Outcome: The proposed framework outperforms state-of-the-art methods under memory constraints.
UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation (2025.findings-emnlp)

Copied to clipboard

Challenge: Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs).
Approach: They propose a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM’s personality traits.
Outcome: The proposed method can modulate the personality expression of large language models by dynamically altering their predicted probability of upcoming words in a pluggable fashion.
Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder (2022.emnlp-main)

Copied to clipboard

Challenge: Existing work reserves the principle dimensions of query and document embeddings for building more efficient retrieval systems.
Approach: They propose to use Conditional Autoencoder to compress high-dimensional embeddings to maintain the same embeddable distribution and better recover ranking features.
Outcome: The proposed algorithm achieves comparable ranking performance with its teacher model and makes the retrieval system more efficient.
Advancing Parameter Efficiency in Fine-tuning via Representation Editing (2024.acl-long)

Copied to clipboard

Challenge: Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters.
Approach: They propose a new approach to fine-tuning neural models that scales and biases the representation produced at each layer.
Outcome: The proposed approach reduces the number of trainable parameters by a factor of 25,700 compared to full parameter fine-tuning and by . 32 compared with LoRA.
Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective (2025.coling-main)

Copied to clipboard

Challenge: Recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) however, limited research into the underlying mechanisms that make LLMs vulnerable to such attacks has been conducted.
Approach: They propose that LLMs' self-safeguarding capability is linked to specific activity patterns within their representation space.
Outcome: The proposed models can be detected with a few pairs of contrastive queries, and the robustness can be manipulated by weakening or strengthening these patterns.
Promoting Data and Model Privacy in Federated Learning through Quantized LoRA (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing federated learning frameworks require substantial data and computational resources to develop large language models.
Approach: They propose a method that distributes a quantized version of the model’s parameters during training and combine it with a popular fine-tuning method to significantly reduce communication costs.
Outcome: The proposed method enables accurate estimations for parameter updates while preventing clients from accessing a model whose performance is comparable to the centrally hosted one.

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