No article text was recorded for this version.
alignment-induced sycophancy
Version 1 of 122 papers32 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Can We Trust AI Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models
- Blog: Factuality of Large Language Models: A Survey
- Blog: A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
- Blog: Towards Understanding Sycophancy in Language Models
- Blog: Deconstructing the ethics of large language models from long-standing issues to new-emerging dilemmas: a survey
- Blog: Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
- Blog: Sycophancy Claims about Language Models: The Missing Human-in-the-Loop
- Blog: LLMs May Perform MCQA by Selecting the Least Incorrect Option
- Blog: Properties and Challenges of LLM-Generated Explanations
- Blog: Are DeepSeek R1 And Other Reasoning Models More Faithful?
- Blog: Online Learning from Strategic Human Feedback in LLM Fine-Tuning
- Blog: Axiomatic Preference Modeling for Longform Question Answering
- Blog: From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
- Blog: Human Feedback is not Gold Standard
- Blog: Studying and improving reasoning in humans and machines
- Blog: Linear Probe Penalties Reduce LLM Sycophancy
- Blog: Medical foundation large language models for comprehensive text analysis and beyond
- Blog: How RLHF Amplifies Sycophancy
- Blog: BLEUBERI: BLEU is a surprisingly effective reward for instruction following
- Blog: Born Pragmatic, Trained to Hallucinate? Quantifying the Origins of Contextual Bias in LLMs via the PaCE Benchmark
- Blog: "I understand your perspective": LLM Persuasion through the Lens of Communicative Action Theory
- Blog: Large Language Models are biased to overestimate profoundness
History & citation
Current · Permanent link
- This direction split from Sycophancy and the Helpfulness-Honesty Trade-off (82% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_alignment_induced_sycophancy_c31525d1,
title = {alignment-induced sycophancy},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/alignment-induced-sycophancy/rdr_c31525d1904c42819a585575c8e8dfaa},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_alignment_induced_sycophancy_c31525d1_v1,
title = {alignment-induced sycophancy},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/alignment-induced-sycophancy/rdr_c31525d1904c42819a585575c8e8dfaa/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}