KABI's repositories
SKP-for-KBQA
The code of CIKM 2023 short paper : Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA
MSDP-Fewshot-NER
The code of CIKM 2023 (Oral Presentation) : A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER
Noise-Slot-Filling-LLM
The Dataset of NLPCC 2023 (Oral Presentation): Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task
dongguanting.github.io
KABI's personal page
do-research-in-AI
A repository of useful research/skill-upgrading talks or acticles in NLP/CV/AI Area (in Chinese).
dpa-rag-anonymous
anonymous code for dparag
FlashRAG
⚡FlashRAG: A Python Toolkit for Efficient RAG Research
json_repair
A python module to repair invalid JSON, commonly used to parse the output of LLMs
KnowPAT
[Paper][ACL 2024 Findings] Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering
LLaVA-CoT
LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning
MTU-Bench
MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models
online_merging_optimizers
Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment
RagLLaVA
Official PyTorch Implementation of MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training.
ReST-MCTS
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)
Umi-OCR_runtime_linux
Umi-OCR Linux 运行环境
VISTA_Evaluation_FineTuning
Evaluation code and datasets for the ACL 2024 paper, VISTA: Visualized Text Embedding for Universal Multi-Modal Retrieval. The original code and model can be accessed at FlagEmbedding.
We-Math
Code and data of We-Math