247 citations · 316 across the 24 of their papers we have counts for
24 papers
Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant Knowledge
Qi Luo, Xiaonan Li, Junqi Dai +2
Retrieval-Augmented Generation has shown remarkable results to address Large Language Models' hallucinations, which usually uses a large external corpus to supplement knowledge to…
Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning
Qi Luo, Xiaonan Li, Tingshuo Fan +2
Retrieval-augmented generation (RAG) has emerged as a leading approach to reducing hallucinations in large language models (LLMs). Current RAG evaluation benchmarks primarily focus…
MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
Qi Luo, Xiaonan Li, Yuxin Wang +4
Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data, resulting in factual inaccuracies and weak adaptability to new…
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
Yuan Li, Qi Luo, Xiaonan Li +7
Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and mitigate hallucination. However, dense retri…
Understanding the Role of LLMs in Multimodal Evaluation Benchmarks
Botian Jiang, Lei Li, Xiaonan Li +5
The rapid advancement of Multimodal Large Language Models (MLLMs) has been accompanied by the development of various benchmarks to evaluate their capabilities. However, the true na…
Case2Code: Scalable Synthetic Data for Code Generation
Yunfan Shao, Linyang Li, Yichuan Ma +11
Large Language Models (LLMs) have shown outstanding breakthroughs in code generation. Recent work improves code LLMs by training on synthetic data generated by some powerful LLMs,…
Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation
Qin Zhu, Qingyuan Cheng, Runyu Peng +5
The training process of large language models (LLMs) often involves varying degrees of test data contamination. Although current LLMs are achieving increasingly better performance…
Scaling Laws for Fact Memorization of Large Language Models
Xingyu Lu, Xiaonan Li, Qinyuan Cheng +3
Fact knowledge memorization is crucial for Large Language Models (LLM) to generate factual and reliable responses. However, the behaviors of LLM fact memorization remain under-expl…
Unified Active Retrieval for Retrieval Augmented Generation
Qinyuan Cheng, Xiaonan Li, Shimin Li +7
In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Therefore, determining whether to retrieve is crucial…
Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models
Zhangyue Yin, Qiushi Sun, Qipeng Guo +9
Recent advancements in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks. Current research enhances…
LLatrieval: LLM-Verified Retrieval for Verifiable Generation
Xiaonan Li, Changtai Zhu, Linyang Li +3
Verifiable generation aims to let the large language model (LLM) generate text with supporting documents, which enables the user to flexibly verify the answer and makes the LLM's o…
Unified Demonstration Retriever for In-Context Learning
Xiaonan Li, Kai Lv, Hang Yan +6
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.…
MoT: Memory-of-Thought Enables ChatGPT to Self-Improve
Xiaonan Li, Xipeng Qiu
Large Language Models (LLMs) have shown impressive abilities in various tasks. However, fundamentally improving them depends on high-quality datasets or computationally expensive f…
Finding Support Examples for In-Context Learning
Xiaonan Li, Xipeng Qiu
Additionally, the strong dependency among in-context examples makes it an NP-hard combinatorial optimization problem and enumerating all permutations is infeasible. Hence we propos…
Soft-Labeled Contrastive Pre-training for Function-level Code Representation
Xiaonan Li, Daya Guo, Yeyun Gong +6
Code contrastive pre-training has recently achieved significant progress on code-related tasks. In this paper, we present \textbf{SCodeR}, a \textbf{S}oft-labeled contrastive pre-t…
An Embarrassingly Easy but Strong Baseline for Nested Named Entity Recognition
Hang Yan, Yu Sun, Xiaonan Li +1
Named entity recognition (NER) is the task to detect and classify the entity spans in the text. When entity spans overlap between each other, this problem is named as nested NER. S…
CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search
Xiaonan Li, Yeyun Gong, Yelong Shen +7
In this paper, we propose the CodeRetriever model, which learns the function-level code semantic representations through large-scale code-text contrastive pre-training. We adopt tw…
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning
Linyang Li, Demin Song, Xiaonan Li +3
\textbf{P}re-\textbf{T}rained \textbf{M}odel\textbf{s} have been widely applied and recently proved vulnerable under backdoor attacks: the released pre-trained weights can be malic…
Accelerating BERT Inference for Sequence Labeling via Early-Exit
Xiaonan Li, Yunfan Shao, Tianxiang Sun +3
Both performance and efficiency are crucial factors for sequence labeling tasks in many real-world scenarios. Although the pre-trained models (PTMs) have significantly improved the…
BERT for Monolingual and Cross-Lingual Reverse Dictionary
Hang Yan, Xiaonan Li, Xipeng Qiu
Reverse dictionary is the task to find the proper target word given the word description. In this paper, we tried to incorporate BERT into this task. However, since BERT is based o…
FLAT: Chinese NER Using Flat-Lattice Transformer
Xiaonan Li, Hang Yan, Xipeng Qiu +1
Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information. However, since the…
TENER: Adapting Transformer Encoder for Named Entity Recognition
Hang Yan, Bocao Deng, Xiaonan Li +1
The Bidirectional long short-term memory networks (BiLSTM) have been widely used as an encoder in models solving the named entity recognition (NER) task. Recently, the Transformer…
Learning Sparse Sharing Architectures for Multiple Tasks
Tianxiang Sun, Yunfan Shao, Xiaonan Li +4
Most existing deep multi-task learning models are based on parameter sharing, such as hard sharing, hierarchical sharing, and soft sharing. How choosing a suitable sharing mechanis…
Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanation
Cunxiang Wang, Shuailong Liang, Yue Zhang +2
Introducing common sense to natural language understanding systems has received increasing research attention. It remains a fundamental question on how to evaluate whether a system…