No article text was recorded for this version.
alignment-induced overconfidence
Version 1 of 151 papers71 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Reliable and Responsible Foundation Models
- Blog: On the Calibration of Large Language Models and Alignment
- Blog: A Study on the Calibration of In-context Learning
- Blog: Rethinking LLM Confidence: From Calibration to Coherence
- Blog: Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models
- Blog: What large language models know and what people think they know
- Blog: When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?
- Blog: Calibrating Large Language Models with Sample Consistency
- Blog: Calibrating Language Models with Adaptive Temperature Scaling
- Blog: BaseCal: Unsupervised Confidence Calibration via Base Model Signals
- Blog: Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs
- Blog: Language Model Probabilities are Not Calibrated in Numeric Contexts
- Blog: Evaluating language models as risk scores
- Blog: Calibrated Language Models and How to Find Them with Label Smoothing
- Blog: Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
- Blog: Can Model Uncertainty Function as a Proxy for Multiple-Choice Question Item Difficulty?
- Blog: Calibrating the Confidence of Large Language Models by Eliciting Fidelity
- Blog: On Diversified Preferences of Large Language Model Alignment
- Blog: Selectively Answering Ambiguous Questions
- Blog: Benchmarking LLMs via Uncertainty Quantification
- Blog: Large Language Models are Miscalibrated In-Context Learners
- Blog: Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs
- Blog: Open-Vocabulary Calibration for Fine-tuned CLIP
- Blog: Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering
- Blog: Investigating the confidence calibratability of deep neural networks Investigating the confidence calibratability of deep neural networks
- Blog: Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
- Blog: How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
- Blog: Calibrating Long-form Generations From Large Language Models
- Blog: Confidence and Correctness Are Indistinguishable to a Prompted Model on Multimodal Geometry
- Blog: Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models
- Blog: VAQUUM: Are Vague Quantifiers Grounded in Visual Data?
- Blog: Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies Between Model Predictions and Human Responses in VQA
- Blog: Do LLM Agents Know How to Ground, Recover, and Assess? Evaluating Epistemic Competence in Information-Seeking Agents
- Blog: Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting
- Blog: Confidence Calibration for Multimodal LLMs: An Empirical Study Through Medical VQA
- Blog: Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models
- Blog: Calibrated Language Models Must Hallucinate
- Blog: Are Language Model Logits Calibrated?
- Blog: Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty
- Blog: Thermometer: Towards Universal Calibration for Large Language Models
- Blog: Predicting Partially Observed Long-Term Outcomes with Adversarial Positive-Unlabeled Domain Adaptation
- Blog: Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
- Blog: Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models
- Blog: Does ChatGPT Know That It Does Not Know? Evaluating the Black-Box Calibration of ChatGPT
- Blog: Taming Overconfidence in LLMs: Reward Calibration in RLHF
- Blog: BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
- Blog: Class-Center-Based Self-Knowledge Distillation: A Simple Method to Reduce Intra-Class Variance
- Blog: The Source of Competence Shapes Metacognition in Language Models
- Blog: Aligning Large Language Models for Faithful Integrity Against Opposing Argument
- Blog: Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
- Blog: Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_alignment_induced_overconfidence_35b369fb,
title = {alignment-induced overconfidence},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/alignment-induced-overconfidence/rdr_35b369fbc1df41c78a1e6b53fc494974},
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_overconfidence_35b369fb_v1,
title = {alignment-induced overconfidence},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/alignment-induced-overconfidence/rdr_35b369fbc1df41c78a1e6b53fc494974/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}