Pinned Repositories
CoT-Collection
[EMNLP 2023] The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning
FLASK
[ICLR 2024 Spotlight] FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
GAP
[ACL 2023] Gradient Ascent Post-training Enhances Language Model Generalization
How-Well-Do-LLMs-Truly-Ground
InstructIR
IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our focuses on user-aligned instructions tailored to each query instance.
Janus
[ACL 2024 NLP4ConvAI Oral] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages
KtrlF
[NAACL 2024] Official repository for "KTRL+F: Knowledge-Augmented In-Document Search"
LangBridge
[ACL 2024] LangBridge: Multilingual Reasoning Without Multilingual Supervision
SelFee
Official codebase for "SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation"
Volcano
[NAACL 2024] Vision language model that reduces hallucinations through self-feedback guided revision. Visualizes attentions on image features for interpretation.
KAIST AI's Repositories
kaistAI/SelFee
Official codebase for "SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation"
kaistAI/FLASK
[ICLR 2024 Spotlight] FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
kaistAI/CoT-Collection
[EMNLP 2023] The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning
kaistAI/LangBridge
[ACL 2024] LangBridge: Multilingual Reasoning Without Multilingual Supervision
kaistAI/Volcano
[NAACL 2024] Vision language model that reduces hallucinations through self-feedback guided revision. Visualizes attentions on image features for interpretation.
kaistAI/Janus
[ACL 2024 NLP4ConvAI Oral] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages
kaistAI/GAP
[ACL 2023] Gradient Ascent Post-training Enhances Language Model Generalization
kaistAI/InstructIR
IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our focuses on user-aligned instructions tailored to each query instance.
kaistAI/KtrlF
[NAACL 2024] Official repository for "KTRL+F: Knowledge-Augmented In-Document Search"
kaistAI/How-Well-Do-LLMs-Truly-Ground
kaistAI/knowledge-reasoning
Official implementation of "Investigating How Large Language Models Leverage Internal Knowledge to Perform Complex Reasoning"
kaistAI/Semiparametric_Token-Sequence_Co-Supervision
kaistAI/ClaimDiff
kaistAI/weather_codes
Summarization module based on KoBART
kaistAI/weather_docker
kaistAI/kaistai.github.io