![]() Eliciting reasoning with promptingĪs opposed to “naive” prompting that requires an input to be directly followed by the output/answer, elicitive prompts encourage LMs to solve tasks by following intermediate steps before predicting the output/answer. Below we discuss several of the mentioned strategies in the ALM paper to augment LLMs to achieve reasoning including: Eliciting reasoning with prompting and Recursive prompting. So for the LLM to be reasoning in this context, we expect it to output an instruction set of how to complete a task when given a prompt. In that sense, reasoning is akin to planning. There exist various ways to decompose into subtasks, such as recursion or iteration. The authors define reasoning in the context of LLMs as the following: Reasoning is decomposing a potentially complex task into simpler subtasks the LM can solve more easily by itself or using tools. ![]() Furthermore, these models typically become more interpretable as the causal means of how an LLM came up with an answer is captured. APIs, programs, or task-specific models). With reasoning capabilities, these models can output a plan of how to solve a task with easier sub-tasks, which can be solved easily by other tools (e.g. The survey paper goes on to explain that language models need to develop reasoning skills (rather than just statistical language modeling). And although the scaling up for the models and their context will always improve things, there’s a need for research to solve these issues. Notably, the issue of having one single parametric model (rather than an ensemble of models working together), and a limited context of typically n previous or surrounding tokens, is a severe limitation. In the recent paper: “Augmented Language Models: a Survey” from Meta AI, the authors argue that statistical language modeling is a fundamental defect of LLMs. Or are these language models just understanding the statistics of language, so that they can pattern-match output well enough to mimic understanding? The question is whether these language models, when the parameters are scaled up, could match human-level intelligence. Despite their groundbreaking capabilities, people argue whether these language models are still missing fundamental parts that make up general intelligence.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |