paper-with-me

Papers

The Capacity for Moral Self-Correction in Large Language Models

2023-02-15 · Deep Ganguli, Amanda Askell, Nicholas Schiefer, Thomas I. Liao, Kamilė Lukošiūtė, Anna Chen, Anna Goldie, Azalia Mirhoseini, Catherine Olsson, Danny Hernandez, Dawn Drain, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jackson Kernion, Jamie Kerr, Jared Mueller, Joshua Landau, Kamal Ndousse, Karina Nguyen, Liane Lovitt, Michael Sellitto, Nelson Elhage, Noemi Mercado, Nova DasSarma, Oliver Rausch, Robert Lasenby, Robin Larson, Sam Ringer, Sandipan Kundu, Saurav Kadavath, Scott Johnston, Shauna Kravec, Sheer El Showk, Tamera Lanham, Timothy Telleen-Lawton, Tom Henighan, Tristan Hume, Yuntao Bai, Zac Hatfield-Dodds, Ben Mann, Dario Amodei, Nicholas Joseph, Sam McCandlish, Tom Brown, Christopher Olah, Jack Clark, Samuel R. Bowman, Jared Kaplan

We test the hypothesis that language models trained with reinforcement learning from human feedback (RLHF) have the capability to "morally self-correct" -- to avoid producing harmful outputs -- if instructed to do so. We find strong evidence in support of this hypothesis across three different experiments, each of which reveal different facets of moral self-correction. We find that the capability for moral self-correction emerges at 22B model parameters, and typically improves with increasing model size and RLHF training. We believe that at this level of scale, language models obtain two capabilities that they can use for moral self-correction: (1) they can follow instructions and (2) they can learn complex normative concepts of harm like stereotyping, bias, and discrimination. As such, they can follow instructions to avoid certain kinds of morally harmful outputs. We believe our results are cause for cautious optimism regarding the ability to train language models to abide by ethical principles.

📄 PDF Abstract BibTeX arXiv:2302.07459

Code (0)

등록된 구현이 없습니다.

Tasks

Language Modelling

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis

2024-07-21 · Guangliang Liu, Haitao Mao, Jiliang Tang, Kristen Marie Johnson

Large Language Models (LLMs) are capable of producing content that perpetuates stereotypes, discrimination, and toxicity. The recently proposed moral self-correction is a computationally efficient method for reducing har…

Question AnsweringText Generation

Discourse Heuristics For Paradoxically Moral Self-Correction

2025-07-01 · Guangliang Liu, Zimo Qi, Xitong Zhang, Kristen Marie Johnson arxiv

Moral self-correction has emerged as a promising approach for aligning the output of Large Language Models (LLMs) with human moral values. However, moral self-correction techniques are subject to two primary paradoxes. F…

Smaller Large Language Models Can Do Moral Self-Correction

2024-10-30 · Guangliang Liu, Zhiyu Xue, Rongrong Wang, Kristen Marie Johnson

Self-correction is one of the most amazing emerging capabilities of Large Language Models (LLMs), enabling LLMs to self-modify an inappropriate output given a natural language feedback which describes the problems of tha…

Language ModelingLanguage ModellingSafety Alignment

On the Convergence of Moral Self-Correction in Large Language Models

2025-10-08 · Guangliang Liu, Haitao Mao, Bochuan Cao, Zhiyu Xue 외 arxiv

Large Language Models (LLMs) are able to improve their responses when instructed to do so, a capability known as self-correction. When instructions provide only a general and abstract goal without specific details about …

Is Moral Self-correction An Innate Capability of Large Language Models? A Mechanistic Analysis to Self-correction

2024-10-27 · Zimo Qi, Guangliang Liu, Kristen Marie Johnson, Lu Cheng

Though intensive attentions to the self-correction capability of Large Language Models (LLMs), the underlying mechanism of this capability is still under-explored. In this paper, we aim to answer two fundamental question…