[arXiv-2023] Instruction-Following Evaluation for Large Language Models

[arXiv-2024] Many-Shot In-Context Learning

[arXiv-2024] Scaling and evaluating sparse autoencoders

[Arxiv-2024] OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement

[ACL-2024] Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning

[Neurips-2023] CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion

[ICLR-2024] What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning

[ArXiv-2023] Instruction Mining: When Data Mining Meets Large Language Model Finetuning

[Neurips-2023] Reflexion: Language Agents with Verbal Reinforcement Learning

[EMNLP-2023] Large Language Models Can Self-Improve

[NAACL-2023] From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning

[ICLR-2023] Copy Is All You Need

[ArXiv-2024] Reliable, Adaptable, and Attributable Language Models with Retrieval

[ArXiv-2024] Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation

[Neurips-2023] LIMA: Less Is More for Alignment

[NAACL-2024] A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

[ArXiv-2023] R-Tuning: Teaching Large Language Models to Refuse Unknown Questions

[ArXiv-2024] Universal and Transferable Adversarial Attacks on Aligned Language Models

[ArXiv-2024] DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

[AAAI-2021] Automated Storytelling via Causal, Commonsense Plot Ordering

[CIKM-2020] Creative Storytelling with Language Models and Knowledge Graphs

[CAIN-2024] Seven Failure Points When Engineering a Retrieval Augmented Generation System