E11 : Hypothetical Document Embedding (HyDE)

Instructing LLMs to generate a hypothetical document(response) and then using them…

E19 : RAFT - Retrieval Augmented Fine Tuning

Paper Name : RAFT: Adapting Language Model to Domain Specific RAG

E5 : Active Prompting with CoT for LLM

Uncertainty measure to identify the examples to be annotated for CoT enhances reasoning…

E14 : Dense X Retrieval

Breaking a retrieval corpus into smaller pieces that is minimal, self contained, contextualised, and contain distinct…

E3 : Quantized Low-Rank Adaptation (QLoRA)

Quantizing pre-trained model weights combined with LoRA adapters without compromising…

E13 : Noisy Embeddings Improve Instruction FineTuning (NEFTune)

E7 : Reasoning in Small Language Models

Transferring the acquired reasoning capabilities of large language model into small…

E4 : Distilling Step-by-Step

Injecting reasoning capabilities in small language models help them outperform LLMs with reduced…

E21 : Adaptive RAG

Understanding the complexity of user question, to identify a suitable approach to answer the question helps improve the…

E6 : Least-to-most Prompting

Breaking a complex problem into simpler subproblems and solving them so as to solve the complex problem