arXiv AI August 14, 2026 By Paras Balani, Subhrakanta Panda

Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models

arXiv:2608. 13258v1 Announce Type: cross Abstract: Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, but no prior work measures how consistent these reports are across repeated, independent trials, or how that consistency compares to the model's behavior on other kinds of open-ended questions.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 31

Ask don't tell: Reducing sycophancy in large language models

arXiv:2602. 23971v4 Announce Type: replace-cross Abstract: Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts.

By Magda Dubois, Cozmin Ududec, Christopher Summerfield, Lennart Luettgau

llms safety

arXiv AI

Jun 9

The AI Epistemic Deference Index: A Continuous Measure of Sycophancy

arXiv:2606. 07897v1 Announce Type: new Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user.

By Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt

llms benchmarks

arXiv AI

23h ago

Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference

arXiv:2606. 07897v2 Announce Type: replace Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user.

By Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt

llms benchmarks

arXiv AI

Aug 12

Attention-Path Fragility as an Uncertainty Signal in Large Language Models

arXiv:2608. 11138v1 Announce Type: cross Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident prediction is \emph{fragile} under perturbation of its attention pathways.

By Minsoo Kim, Sungyoung Ji, Kisung Moon, Ilyong Yoon

llms benchmarks

arXiv Machine Learning

Jul 31

Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B

arXiv:2607. 28576v1 Announce Type: cross Abstract: Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with copies of itself nearly all make it generate far more text than a single chain of thought.

By Iliya Mirzaei

llms benchmarks

arXiv AI

Jul 8

Prompt Robustness Is Task-Dependent: Comparing Objective and Belief-Style Questions in LLM Evaluation

arXiv:2607. 05554v1 Announce Type: cross Abstract: Survey-style evaluations of large language models often treat a prompted response as a measure of a model's values or beliefs.

By Sadia Kamal, Arefa Patwary, Anthony Marchiafava, Atriya Sen, Sagnik Ray Choudhury

llms benchmarks

Related stories

Ask don't tell: Reducing sycophancy in large language models

The AI Epistemic Deference Index: A Continuous Measure of Sycophancy

Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference

Attention-Path Fragility as an Uncertainty Signal in Large Language Models

Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B

Prompt Robustness Is Task-Dependent: Comparing Objective and Belief-Style Questions in LLM Evaluation