Copertina

Challenging the Evaluator: LLM Sycophancy Under User Rebuttal

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Sungwon, Khashabi, Daniel
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Evaluating the Evaluators: Are readability metrics good measures of readability?
di: Cachola, Isabel, et al.
Pubblicazione: (2025)

RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind
di: He, Zhitao, et al.
Pubblicazione: (2026)

GOLD PANNING: Strategic Context Shuffling for Needle-in-Haystack Reasoning
di: Byerly, Adam, et al.
Pubblicazione: (2025)

SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning
di: Li, Tianjian, et al.
Pubblicazione: (2025)

Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems
di: Byerly, Adam, et al.
Pubblicazione: (2024)

arXiv2Table: Toward Realistic Benchmarking and Evaluation for LLM-Based Literature-Review Table Generation
di: Wang, Weiqi, et al.
Pubblicazione: (2025)

Measuring Opinion Bias and Sycophancy via LLM-based Persuasion
di: Nogueira, Rodrigo, et al.
Pubblicazione: (2026)

Measuring Sycophancy of Language Models in Multi-turn Dialogues
di: Hong, Jiseung, et al.
Pubblicazione: (2025)

Not Your Typical Sycophant: The Elusive Nature of Sycophancy in Large Language Models
di: Natan, Shahar Ben, et al.
Pubblicazione: (2026)

Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell
di: Lu, Taiming, et al.
Pubblicazione: (2024)

Certified Mitigation of Worst-Case LLM Copyright Infringement
di: Zhang, Jingyu, et al.
Pubblicazione: (2025)

Hell or High Water: Evaluating Agentic Recovery from External Failures
di: Wang, Andrew, et al.
Pubblicazione: (2025)

Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs
di: Vennemeyer, Daniel, et al.
Pubblicazione: (2025)

Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy
di: Feng, Zhaoxin, et al.
Pubblicazione: (2026)

RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
di: Wu, Sihong, et al.
Pubblicazione: (2026)

RORA: Robust Free-Text Rationale Evaluation
di: Jiang, Zhengping, et al.
Pubblicazione: (2024)

The Flaw of Averages: Quantifying Uniformity of Performance on Benchmarks
di: Uzunoglu, Arda, et al.
Pubblicazione: (2025)

Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
di: Uzunoglu, Arda, et al.
Pubblicazione: (2026)

It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty
di: Guo, Kevin H., et al.
Pubblicazione: (2026)

Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA
di: Zhang, Kaiwei, et al.
Pubblicazione: (2025)

BASIL: Bayesian Assessment of Sycophancy in LLMs
di: Atwell, Katherine, et al.
Pubblicazione: (2025)

Sycophancy Hides Linearly in the Attention Heads
di: Genadi, Rifo, et al.
Pubblicazione: (2026)

Many-Tier Instruction Hierarchy in LLM Agents
di: Zhang, Jingyu, et al.
Pubblicazione: (2026)

Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment
di: Kwon, Jea, et al.
Pubblicazione: (2025)

Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate
di: Yao, Binwei, et al.
Pubblicazione: (2025)

TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models
di: Liu, Joshua, et al.
Pubblicazione: (2025)

Sycophancy in Large Language Models: Causes and Mitigations
di: Malmqvist, Lars
Pubblicazione: (2024)

Sycophancy Claims about Language Models: The Missing Human-in-the-Loop
di: Batzner, Jan, et al.
Pubblicazione: (2025)

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
di: Mishra, Aayush, et al.
Pubblicazione: (2025)

Do pretrained Transformers Learn In-Context by Gradient Descent?
di: Shen, Lingfeng, et al.
Pubblicazione: (2023)

WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment
di: Ou, Jiefu, et al.
Pubblicazione: (2024)

Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation
di: Wang, Hexuan, et al.
Pubblicazione: (2026)

Accounting for Sycophancy in Language Model Uncertainty Estimation
di: Sicilia, Anthony, et al.
Pubblicazione: (2024)

BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases
di: Koretsky, Mathew J., et al.
Pubblicazione: (2025)

Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs
di: Sahoo, Subramanyam
Pubblicazione: (2026)

"Check My Work?": Measuring Sycophancy in a Simulated Educational Context
di: Arvin, Chuck
Pubblicazione: (2025)

SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy
di: Bhalla, Joy, et al.
Pubblicazione: (2026)

Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection
di: Park, Sungwon, et al.
Pubblicazione: (2024)

Crystal: Characterizing Relative Impact of Scholarly Publications
di: Collison, Hannah, et al.
Pubblicazione: (2026)

Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback
di: Jiang, Dongwei, et al.
Pubblicazione: (2025)