Chain-of-Thought Prompting Elicits Reasoning in Large Language Models - Leitura de Artigo

https://arxiv.org/pdf/2201.11903.pdf

Chain-of-Thought (CoT) para elaborar perguntas aos LLMs mas as perguntas podem ser incompletas no que diz respeito ao contexto.

A busca exploratório é formada por várias perguntas elaboradas ao longo do processo.

Está relacionado com "Fine Tuning" na tarefa a ser executada pq está ensinando ao LLM como responder

Introduction 

However, scaling up model size alone has not proved sufficient for achieving high performance on challenging tasks such as arithmetic, commonsense, and symbolic reasoning (Raeet al., 2021).
This work explores how the reasoning ability of large language models can be unlocked by a simple method motivated by two ideas. First, techniques for arithmetic reasoning can benefit from generating natural language rationales that lead to the final answer. Prior work has given models the ability to generate natural language intermediate steps by training from scratch (Ling et al., 2017) or finetuning a pretrained model (Cobbe et al., 2021), in addition to neuro-symbolic methods that use formal languages instead of natural language (Roy and Roth, 2015; Chiang and Chen, 2019; Amini et al., 2019; Chen et al., 2019). Second, large language models offer the exciting prospect of in-context few-shot learning via prompting. That is, instead of finetuning a separate language model checkpoint for each new task, one can simply “prompt” the model with a few input–output exemplars demonstrating the task. Remarkably, this has been successful for a range of simple question-answering tasks (Brown et al., 2020).

In this paper, we combine the strengths of these two ideas in a way that avoids their limitations.
Specifically, we explore the ability of language models to perform few-shot prompting for reasoning tasks, given a prompt that consists of triples: 〈input, chain of thought, output〉. A chain of thought is a series of intermediate natural language reasoning steps that lead to the final output, and we refer to
this approach as chain-of-thought prompting.

Chain-of-Thought Prompting

Chain-of-thought prompting has several attractive properties as an approach for facilitating reasoning in language models.
1. First, chain of thought, in principle, allows models to decompose multi-step problems into intermediate steps, which means that additional computation can be allocated to problems that require more reasoning steps.

[Pergunta 1: WHAT, Pergunta 2: WHEN, Pergunta 3: WHERE, Pergunta 4: WHO SAID (Where is written, When was acessed, How it was generated ... All contextualized (possible) answers já se antecipa as perguntas 2 em diante]

2. Second, a chain of thought provides an interpretable window into the behavior of the model, suggesting how it might have arrived at a particular answer and providing opportunities to debug where the reasoning path went wrong (although fully characterizing a model’s computations that support an answer remains an open question).
3. Third, chain-of-thought reasoning can be used for tasks such as math word problems, commonsense reasoning, and symbolic manipulation, and is potentially applicable (at least in principle) to any task that humans can solve via language.
4. Finally, chain-of-thought reasoning can be readily elicited in sufficiently large off-the-shelf language models simply by including examples of chain of thought sequences into the exemplars of few-shot prompting.

Chain-of-thought prompting is a general approach that is inspired by several prior directions: prompt-
ing, natural language explanations, program synthesis/execution, numeric and logical reasoning, and
intermediate language steps.

[Inspiração para transformar Competency Quesitons do KG em Graph Queries via LLM]

Seminário da Pós (YouTube) - 15/09, 15h - On the Construction of Database Interfaces based on Large Language Models

https://www.youtube.com/live/b1I2EQ5rclI?si=9nsS85vl2WMb6aeh