Papers by Xiaonan Li

21 papers
LLatrieval: LLM-Verified Retrieval for Verifiable Generation (2024.naacl-long)

Copied to clipboard

Challenge: Large language models struggle with factual errors and often produce non-factual and fabricated content.
Approach: They propose to use large language models to generate text with supporting documents to enable the user to flexibly verify the answer.
Outcome: Experiments on ALCE show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results.
BERT for Monolingual and Cross-Lingual Reverse Dictionary (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to find the proper word for a word are based on the surface form of words, but they cannot extract the semantic meaning.
Approach: They propose a method to make BERT generate the target word for this task . cross-lingual reverse dictionary is the task to find the proper target word .
Outcome: The proposed method can generate the target word for cross-lingual reverse dictionary task even without the parallel corpus.
Finding Support Examples for In-Context Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: In-context learning is a new learning paradigm where a language model observes a few examples and directly outputs the test input’s prediction.
Approach: They propose a method to find “support examples” for in-context learning by filtering a training dataset and a progressive filtering process to filter out uninformative examples.
Outcome: The proposed method outperforms baselines and shows that each component contributes critically to the improvements.
Unified Demonstration Retriever for In-Context Learning (2023.acl-long)

Copied to clipboard

Challenge: In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction.
Approach: They propose a single model to retrieve demonstrations for a wide range of tasks by combining training signals from various tasks into a unified list-wise ranking formulation by language model’s feedback.
Outcome: The proposed model outperforms baselines on 30+ tasks across 13 task families and multiple data domains.
An Embarrassingly Easy but Strong Baseline for Nested Named Entity Recognition (2023.acl-short)

Copied to clipboard

Challenge: Named entity recognition (NER) is the task to detect and classify entity spans in text.
Approach: They propose to use Convolutional Neural Network to model spatial relations in NER . they use three commonly used nested NER datasets to compare their results .
Outcome: The proposed model outperforms several proposed methods with the same pre-trained encoders in three nested NER datasets.
Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation (2024.findings-emnlp)

Copied to clipboard

Challenge: Current LLMs are achieving better performance on various benchmarks, but their performance in practical applications does not always match their benchmark results.
Approach: They propose to detect and rewrite leaked benchmarks without altering their difficulties by using Inference-Time Decontamination (ITD) to mitigate performance inflation caused by memorizing leaked samples.
Outcome: The proposed method reduces inflated accuracy by 22.9% on GSM8K and 19.0% on MMLU.
Reasoning in Flux: Enhancing Large Language Models Reasoning through Uncertainty-aware Adaptive Guidance (2024.acl-long)

Copied to clipboard

Challenge: Extensive experiments across various reasoning tasks demonstrate that UAG not only enhances the reasoning abilities of LLMs but consistently outperforms several strong baselines with minimal computational overhead.
Approach: They propose an approach to guide LLMs onto an accurate and reliable trajectory by identifying and adjusting uncertainty signals within each step of the reasoning chain.
Outcome: The proposed approach outperforms strong baselines and outperformed strong models with minimal computational overhead.
Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition (2025.emnlp-main)

Copied to clipboard

Challenge: Existing research on long-context scaling in language models has focused on managing lengthy input prompts instead of producing long outputs.
Approach: They propose a sequence-level curriculum learning framework that shifts a model’s focus from interpreting long chain-of-thoughts to generating them.
Outcome: Experiments on rigorous reasoning benchmarks, including AIME24 and GPQA Diamond, show that the proposed approach surpasses standard fine-tuning by over 10% while maintaining robust performance on understanding tasks.
Accelerating BERT Inference for Sequence Labeling via Early-Exit (2021.acl-long)

Copied to clipboard

Challenge: Existing early-exit mechanisms are designed for sequence-level tasks, rather than sequence labeling.
Approach: They propose to extend sentence-level early-exit to accelerate inference of PTMs . they propose a token-level mechanism that allows partial tokens to exit early at different layers .
Outcome: The proposed approach can save up to 66%75% inference cost with minimal performance degradation.
Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation (P19-1)

Copied to clipboard

Challenge: Existing benchmarks measure common sense knowledge indirectly or without reasoning.
Approach: They propose a benchmark to test whether a system can differentiate natural language statements that make sense from those that do not make sense.
Outcome: The proposed benchmarks show that models trained on large corpora perform better than humans on some benchmarks.
MoT: Memory-of-Thought Enables ChatGPT to Self-Improve (2023.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown impressive abilities on various tasks. however, fundamentally improving them depends on high-quality datasets or computationally expensive fine-tuning.
Approach: They propose a framework to let Large Language Models self-improve without annotated datasets or parameter updates.
Outcome: The proposed framework can help ChatGPT significantly improve its abilities in arithmetic reasoning, commonsense reasoning, factual reasoning, and natural language inference.
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: RAG systems that integrate external knowledge with Large Language Models often become bottlenecks due to their limited parameters compared to LLMs and their inability to perform step-by-step reasoning.
Approach: They propose a model that integrates external knowledge with Large Language Models to enhance factual correctness and mitigate hallucination.
Outcome: The proposed model outperforms baselines and can transfer well to different retrievers.
CodeRetriever: A Large Scale Contrastive Pre-Training Method for Code Search (2022.emnlp-main)

Copied to clipboard

Challenge: Existing code pre-training approaches often adopt (masked) language modeling as the training objective which targets on learning to predict (macked) tokens in a given code context.
Approach: They propose a code-text contrastive learning model which learns function-level code semantic representations through large-scale code corpus.
Outcome: The proposed model achieves new state-of-the-art with significant improvement over existing pre-trained models on eleven domain/language-specific code search tasks with six programming languages in different code granularity.
Soft-Labeled Contrastive Pre-Training for Function-Level Code Representation (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for contrastive pre-training ignore the relevance between codes in large code corpus.
Approach: They propose a Soft-labeled contrastive pre-training framework with positive sample construction methods to learn functional-level code representation.
Outcome: The proposed framework can obtain fine-grained soft-labels through an iterative adversarial manner and use them to learn better code representation.
Unified Active Retrieval for Retrieval Augmented Generation (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing active retrieval methods struggle with handling various types of instructions.
Approach: They propose a unified active retrieval framework for retrieval-augmented generation . they propose to combine four orthogonal criteria into plug-and-play classification tasks .
Outcome: The proposed framework outperforms existing methods on four representative types of user instructions on four types of instructions.
UTC-IE: A Unified Token-pair Classification Architecture for Information Extraction (2023.acl-long)

Copied to clipboard

Challenge: Information Extraction (IE) tasks have been solved with different models because of their output structures.
Approach: They propose a Unified Token-pair Classification architecture for Information Extraction that introduces Plusformer on top of the token-pear feature matrix.
Outcome: The proposed approach outperforms task-specific and unified models on all tasks in 10 datasets and achieves better results on 2 joint IE datasets.
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning (2021.emnlp-main)

Copied to clipboard

Challenge: Pre-trained models can be maliciously poisoned with certain triggers, causing a security threat.
Approach: They propose a stronger weight poisoning attack method that introduces a layerwise weight poison strategy to plant deeper backdoors.
Outcome: The proposed method can be widely applied and provide hints for future models robustness studies.
Scaling Laws for Fact Memorization of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Fact knowledge memorization is crucial for Large Language Models (LLMs) to generate factual and reliable responses.
Approach: They analyze scaling laws for LLM’s fact knowledge and LLMs’ behaviors of memorizing different types of facts.
Outcome: The proposed model can generalize on unseen facts and its scaling law is similar to general pre-training.
Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks.
Approach: They propose a hierarchical reasoning aggregation framework to address this problem . they propose dynamic sampling to adjust the number of reasoning chains .
Outcome: The proposed framework outperforms existing ensemble methods on complex reasoning tasks.
Case2Code: Scalable Synthetic Data for Code Generation (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown outstanding breakthroughs in code generation.
Approach: They propose a case-to-code induction task that exploits the expressiveness and correctness of programs by incorporating LLMs into their training.
Outcome: The proposed task improves distribution case-to-code induction and various coding generation tasks.
FLAT: Chinese NER Using Flat-Lattice Transformer (2020.acl-main)

Copied to clipboard

Challenge: Named entity recognition (NER) models are difficult to use because of the complex nature of the lattice structure and the low inference speed.
Approach: They propose a character-word lattice structure that converts lattics into flat structures consisting of spans.
Outcome: The proposed model outperforms other lexicon-based models on four datasets and is highly parallel.

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