#
zxlzr
Follow
Lists (3)
Starred repositories
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
Circuit-Aware Editing Enables Generalizable Knowledge Learners
OneKE is a knowledge extraction framework based on a large model, with preliminary generalized knowledge extraction capabilities in both Chinese and English and in multiple fields and tasks.
LookAhead Tuning: Safer Language Models via Partial Answer Previews
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
[ICLR 2025] Benchmarking Agentic Workflow Generation
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following
DSBench: How Far are Data Science Agents from Becoming Data Science Experts?
[WWW 2025] A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System.
[EMNLP 2024 Findings] OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs.
Comprehensive Evaluation On Answer Calibration For Multi-Step Reasoning
Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation
[TrustNLP@NAACL 2025] BiasEdit: Debiasing Stereotyped Language Models via Model Editing
[EMNLP 2024] To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
Exploring Model Kinship for Merging Large Language Models
[NeurIPS 2024] Agent Planning with World Knowledge Model
Official codes for COLING 2024 paper "Robust and Scalable Model Editing for Large Language Models": https://arxiv.org/abs/2403.17431v1
[ACL 2024] OceanGPT: A Large Language Model for Ocean Science Tasks
Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]
WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining …
[ACL 2024] Learning to Edit: Aligning LLMs with Knowledge Editing
[ACL 2024] An Easy-to-use Hallucination Detection Framework for LLMs.
[NLPCC 2024] Shared Task 10: Regulating Large Language Models