Skip to content
AI News HubLIVE
Original source2 min read

Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning

Summary

This ICML 2026 position paper argues that in high-stakes settings, accurate AI is not enough: systems should reason in ways similar to their users and faithfully communicate that reasoning, an idea the authors call cognitive alignment. It reviews evidence that such alignment improves understandability and trustworthiness, presents new survey data showing many users consider it essential when an AI's rationale matters to them, and lays out gaps in current alignment methods plus a research agenda to close them.

SourcearXiv AIAuthor: Vijay Keswani, Breanna K. Nguyen, Cyrus Cousins, Vincent Conitzer, Walter Sinnott-Armstrong, Jana Schaich Borg
Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 20 Jul 2026]

Title:Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning

View a PDF of the paper titled Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning, by Vijay Keswani and 5 other authors

View PDF HTML (experimental)

Abstract:AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settings, particularly high-stakes decision-making, we need accurate cognitively-aligned AI systems that reason similarly to their users, and faithfully communicate their reasoning. We review evidence that cognitive alignment improves understandability and trustworthiness, and provide new survey data showing that many users find cognitive alignment "essential" when an AI's rationale for a judgment or action is important to them. We outline the gaps between existing alignment methods and what is needed to achieve cognitive alignment, and present a research agenda to address these gaps. We argue that cognitive misalignment represents a likely impediment to AI adoption in many envisioned applications, and that addressing it is important for creating AI systems on which users are both willing and justified to rely.

Comments: Accepted in ICML 2026

Subjects:

Artificial Intelligence (cs.AI); Computers and Society (cs.CY)

Cite as: arXiv:2608.12372 [cs.AI]

(or arXiv:2608.12372v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.12372

arXiv-issued DOI via DataCite

Submission history

From: Vijay Keswani [view email] [v1] Mon, 20 Jul 2026 10:15:50 UTC (600 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning, by Vijay Keswani and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-08

Change to browse by:

cs cs.CY

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • The paper introduces "cognitive alignment": AI that reasons similarly to its users and faithfully communicates its reasoning.
  • New survey data shows many users call cognitive alignment "essential" when an AI's rationale for a judgment or action matters to them.
  • The authors argue cognitive misalignment likely impedes AI adoption in many envisioned applications and propose a research agenda.
  • The position paper, accepted at ICML 2026, is by Vijay Keswani and five co-authors.

Highlights and analysis are generated automatically and may contain errors. Check the original source.