# On the Intersection of Self-Correction and Trust in Language Models

arXiv: https://arxiv.org/abs/2311.02801 · HTML: https://mlsanity.com/paper/2311.02801/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 6 Nov 2023.

## Builds on (most cited first, 19 of 19)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Holistic Evaluation of Language Models](https://mlsanity.com/paper/2211.09110/) (2022)
- [A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation](https://mlsanity.com/paper/2305.11391/) (2023)
- [Post Hoc Explanations of Language Models Can Improve Language Models](https://mlsanity.com/paper/2305.11426/) (2023)
- [A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness](https://mlsanity.com/paper/2212.09006/) (2022)
- [In-Context Explainers: Harnessing LLMs for Explaining Black Box Models](https://mlsanity.com/paper/2310.05797/) (2023)
- [Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context](https://mlsanity.com/paper/2007.08911/) (2020)

## Built on by (most cited first, 12 of 12)

- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment](https://mlsanity.com/paper/2311.08596/) (2023)
- [SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses](https://mlsanity.com/paper/2404.04298/) (2024)
- [Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias](https://mlsanity.com/paper/2407.15366/) (2024)
- [On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept](https://mlsanity.com/paper/2406.02378/) (2024)
- [Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis](https://mlsanity.com/paper/2407.15286/) (2024)
- [Understanding the Effects of Iterative Prompting on Truthfulness](https://mlsanity.com/paper/2402.06625/) (2024)
- [Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning](https://mlsanity.com/paper/2502.05675/) (2025)
- [The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems](https://mlsanity.com/paper/2510.24831/) (2025)
- [MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique](https://mlsanity.com/paper/2511.09067/) (2025)
- [On the Convergence of Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2510.07290/) (2025)
- [A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content](https://mlsanity.com/paper/2504.16120/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex cognitive tasks. However, their complexity and lack of transparency have raised several trustworthiness concerns, including the propagation of misinformation and toxicity. Recent research has explored the self-correction capabilities of LLMs to enhance their performance. In this work, we investigate whether these self-correction capabilities can be harnessed to improve the trustworthiness of LLMs. We conduct experiments focusing on two key aspects of trustworthiness: truthfulness and toxicity. Our findings reveal that self-correction can lead to improvements in toxicity and truthfulness, but the extent of these improvements varies depending on the specific aspect of trustworthiness and the nature of the task. Interestingly, our study also uncovers instances of "self-doubt" in LLMs during the self-correction process, introducing a new set of challenges that need to be addressed.