Automatically Correcting Large Language Models: Surveying the landscape
of diverse self-correction strategies
- URL: http://arxiv.org/abs/2308.03188v2
- Date: Wed, 30 Aug 2023 03:47:34 GMT
- Title: Automatically Correcting Large Language Models: Surveying the landscape
of diverse self-correction strategies
- Authors: Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang,
William Yang Wang
- Abstract summary: Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks.
A promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output.
This paper presents a comprehensive review of this emerging class of techniques.
- Score: 104.32199881187607
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large language models (LLMs) have demonstrated remarkable performance across
a wide array of NLP tasks. However, their efficacy is undermined by undesired
and inconsistent behaviors, including hallucination, unfaithful reasoning, and
toxic content. A promising approach to rectify these flaws is self-correction,
where the LLM itself is prompted or guided to fix problems in its own output.
Techniques leveraging automated feedback -- either produced by the LLM itself
or some external system -- are of particular interest as they are a promising
way to make LLM-based solutions more practical and deployable with minimal
human feedback. This paper presents a comprehensive review of this emerging
class of techniques. We analyze and taxonomize a wide array of recent work
utilizing these strategies, including training-time, generation-time, and
post-hoc correction. We also summarize the major applications of this strategy
and conclude by discussing future directions and challenges.
Related papers
- Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing [56.75702900542643]
We introduce AlphaLLM for the self-improvements of Large Language Models.
It integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop.
Our experimental results show that AlphaLLM significantly enhances the performance of LLMs without additional annotations.
arXiv Detail & Related papers (2024-04-18T15:21:34Z) - Debiasing Multimodal Large Language Models [61.6896704217147]
Large Vision-Language Models (LVLMs) have become indispensable tools in computer vision and natural language processing.
Our investigation reveals a noteworthy bias in the generated content, where the output is primarily influenced by the underlying Large Language Models (LLMs) prior to the input image.
To rectify these biases and redirect the model's focus toward vision information, we introduce two simple, training-free strategies.
arXiv Detail & Related papers (2024-03-08T12:35:07Z) - Adversarial Math Word Problem Generation [6.92510069380188]
We propose a new paradigm for ensuring fair evaluation of large language models (LLMs)
We generate adversarial examples which preserve the structure and difficulty of the original questions aimed for assessment, but are unsolvable by LLMs.
We conduct experiments on various open- and closed-source LLMs, quantitatively and qualitatively demonstrating that our method significantly degrades their math problem-solving ability.
arXiv Detail & Related papers (2024-02-27T22:07:52Z) - Pedagogical Alignment of Large Language Models [24.427653091950994]
We introduce the novel concept of pedagogically aligned Large Language Models (LLMs)
LLMs function as scaffolding tools, breaking complex problems into manageable subproblems and guiding students towards the final answer through constructive feedback and hints.
This study reinterprets the narrative by viewing the task through the lens of alignment and demonstrates how RLHF methods emerge naturally as a superior alternative.
arXiv Detail & Related papers (2024-02-07T16:15:59Z) - Large Language Models Cannot Self-Correct Reasoning Yet [78.16697476530994]
Large Language Models (LLMs) have emerged as a groundbreaking technology with their unparalleled text generation capabilities.
Concerns persist regarding the accuracy and appropriateness of their generated content.
A contemporary methodology, self-correction, has been proposed as a remedy to these issues.
arXiv Detail & Related papers (2023-10-03T04:56:12Z) - Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools.
Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions.
Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
arXiv Detail & Related papers (2023-09-20T09:23:46Z) - Editing Large Language Models: Problems, Methods, and Opportunities [51.903537096207]
This paper embarks on a deep exploration of the problems, methods, and opportunities related to model editing for LLMs.
We provide an exhaustive overview of the task definition and challenges associated with model editing, along with an in-depth empirical analysis of the most progressive methods currently at our disposal.
Our objective is to provide valuable insights into the effectiveness and feasibility of each editing technique, thereby assisting the community in making informed decisions on the selection of the most appropriate method for a specific task or context.
arXiv Detail & Related papers (2023-05-22T16:00:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.