NLP
29 文章 × 121640 字
2024
28篇
+
09-13
[arXiv-2023] Instruction-Following Evaluation for Large Language Models
09-11
[arXiv-2024] Many-Shot In-Context Learning
09-04
[arXiv-2024] Scaling and evaluating sparse autoencoders
08-01
The Llama 3 Herd of Models
07-25
[Arxiv-2024] OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
07-05
[ACL-2024] Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning
05-05
[Neurips-2023] CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
04-21
[ICLR-2024] What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
04-10
[ArXiv-2023] Instruction Mining: When Data Mining Meets Large Language Model Finetuning
04-09
[Neurips-2023] Reflexion: Language Agents with Verbal Reinforcement Learning
04-08
[EMNLP-2023] Large Language Models Can Self-Improve
04-07
[NAACL-2023] From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
04-07
[ICLR-2023] Copy Is All You Need
04-03
[ArXiv-2024] Reliable, Adaptable, and Attributable Language Models with Retrieval
04-01
[ArXiv-2024] Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
04-01
[Neurips-2023] LIMA: Less Is More for Alignment
03-25
[ArXiv-2023] One Shot Learning as Instruction Data Prospector for Large Language Models
03-19
[ICLR-2024] GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
03-19
[NAACL-2024] A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
03-14
[ArXiv-2023] R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
03-06
[ArXiv-2024] Universal and Transferable Adversarial Attacks on Aligned Language Models
03-05
[ArXiv-2024] DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
02-29
[AAAI-2021] Automated Storytelling via Causal, Commonsense Plot Ordering
02-12
使用 spaCy / OpenIE 从文本中提取三元组
02-12
[CIKM-2020] Creative Storytelling with Language Models and Knowledge Graphs
02-03
hf-mirror
02-02
ChatGLM3-6B sft时报错`Error: No such option: -- deepspeed`
02-01
[CAIN-2024] Seven Failure Points When Engineering a Retrieval Augmented Generation System