> For the complete documentation index, see [llms.txt](https://ubiai.gitbook.io/llm-guide/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ubiai.gitbook.io/llm-guide/directory-of-links-by-section.md).

# Directory of Links By Section

### Introduction

* [Transformer Paper: Attention Is All You Need ](https://arxiv.org/abs/1706.03762)– The foundational paper on Transformers.

### Prompt Engineering

* [Language Models are Few-Shot Learners](https://arxiv.org/abs/2005.14165) – Describes LLMs ability to perform a wide range of tasks with few-shot learning.
* [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://arxiv.org/abs/2201.11903) – Explores how chain-of-thought prompting improves reasoning in LLMs.
* [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://arxiv.org/abs/2203.11171) – Shows how generating multiple responses can improve reasoning consistency.
* [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://arxiv.org/pdf/2305.10601) – Introduces the Tree of Thought approach to enhance reasoning capabilities in LLMs.
* [Logic-of-Thought ](https://arxiv.org/abs/2409.17539)–  Injecting Logic into Contexts for Full Reasoning in Large Language Models

### Neuro-Symbolic Methods

* [Large Language Models Are Neurosymbolic Reasoners](https://arxiv.org/abs/2401.09334) - This paper investigates the potential application of Large Language Models (LLMs) as symbolic reasoners.

### Retrieval-Augmented Generation (RAG)

* [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/abs/2005.11401) – Introduces RAG, a method combining retrieval-based and generation-based models to enhance the performance on knowledge-intensive tasks.

### Honorable Mentions

* [Distilling the Knowledge in a Neural Network](https://arxiv.org/abs/1503.02531) – Foundational paper on knowledge distillation.
* [Popular Ensemble Methods](https://arxiv.org/pdf/1106.0257) – Overview paper on ensemble methods and voting systems.

### Fine-Tuning

* [Stochastic Gradient Descent](https://arxiv.org/abs/1412.6980) – This paper discusses the use of Stochastic Gradient Descent (SGD) for Machine Learning.
* [Learning to Summarize with Human Feedback](https://arxiv.org/abs/2009.01325) – This paper introduces Reinforcement Learning from Human Feedback (RLHF).

### Full Parameter Fine-Tuning

* [AdamW Documentation](https://pytorch.org/docs/stable/generated/torch.optim.AdamW.html) – Official documentation for the AdamW optimizer in PyTorch, widely used for fine-tuning models.
* [LIFT ](https://openreview.net/pdf?id=u0INlprg3U)– The paper introducing Layer-wise Fine-Tuning (LIFT) for model adaptation.
* [Hugging Face Transformers Library](https://github.com/huggingface/transformers) – A popular library for working with pre-trained transformer models, including support for fine-tuning tasks.

### Parameter-Efficient Fine-Tuning (PEFT)

* [LoRA (Low-Rank Adaptation) Paper](https://arxiv.org/abs/2106.09685) – The original paper discussing Low-Rank Adaptation (LoRA), a technique for efficient fine-tuning of large pre-trained models.
* [PEFT Documentation](https://github.com/huggingface/peft) – Documentation for the PEFT (Parameter-Efficient Fine-Tuning) technique, including implementation and configurations related to LoRA and other efficient fine-tuning approaches.
* [Rotten Tomatoes Dataset ](https://huggingface.co/datasets/cornell-movie-review-data/rotten_tomatoes)– The Rotten Tomatoes dataset, used for sentiment analysis and fine-tuning tasks in this example.
* [Hugging Face Transformers Library](https://github.com/huggingface/transformers) – A popular library for working with pre-trained transformer models, including support for fine-tuning tasks.

### Task specific Evaluation Metrics

* [PyTorch Documentation](https://pytorch.org/docs/stable/) - Official documentation for PyTorch, including tools for implementing perplexity calculations.
* [NLTK BLEU Documentation](https://www.nltk.org/api/nltk.translate.bleu_score.html) - Official documentation for the NLTK library, which includes BLEU score calculation.
* [Rouge Score GitHub](https://github.com/google-research/google-research/tree/master/rouge) - GitHub repository for the ROUGE metric, used for evaluating text summaries.
* [NLTK Meteor Documentation](https://www.nltk.org/api/nltk.translate.meteor_score.html) - NLTK’s official documentation for METEOR score, an alternative to BLEU.
* [python-Levenshtein GitHub](https://github.com/ztane/python-Levenshtein) - GitHub repository for the Python-Levenshtein package, which implements Levenshtein distance.
* [Scikit-learn GitHub Repository](https://github.com/scikit-learn/scikit-learn) - GitHub repository for scikit-learn, which provides implementations of F1 score and other classification metrics.

### Popular Benchmarks

* [GLUE (General Language Understanding Evaluation)](https://gluebenchmark.com/) - A widely used benchmark in NLP that tests models on tasks such as sentiment analysis, textual entailment, and factual question answering to assess general-purpose language understanding.
* [SuperGLUE](https://super.gluebenchmark.com/) - An advanced version of GLUE that includes more complex tasks like commonsense reasoning, multi-hop inference, and complex question answering to push the boundaries of LLM capabilities.
* [MMLU (Massive Multitask Language Understanding)](https://paperswithcode.com/dataset/mmlu) - A benchmark designed to evaluate LLMs on 57 diverse tasks, from elementary school-level math to advanced subjects like law and medicine, testing reasoning and domain-specific knowledge.
* [SQuAD (Stanford Question Answering Dataset) ](https://rajpurkar.github.io/SQuAD-explorer/)- A benchmark for evaluating a model's reading comprehension and question-answering capabilities, with two versions: SQuAD 1.1 (answer extraction) and SQuAD 2.0 (including unanswerable questions).
* [HellaSwag](https://paperswithcode.com/dataset/hellaswag) - A benchmark for testing commonsense reasoning and contextual understanding by predicting the most likely continuation of incomplete sentences or narratives in multiple-choice format.
* [WinoGrande ](https://paperswithcode.com/dataset/winogrande)- A benchmark focused on coreference resolution, particularly resolving pronouns in complex sentences, to assess a model's ability to understand relationships between entities in a document.