Cover Image

Does Alignment Tuning Really Break LLMs' Internal Confidence?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Oh, Hongseok, Hwang, Wonseok
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do Vision Encoders Truly Explain Object Hallucination?: Mitigating Object Hallucination via Simple Fine-Grained CLIPScore
by: Oh, Hongseok, et al.
Published: (2025)

Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs' Legal Reasoning Capabilities
by: Oh, Hongseok, et al.
Published: (2025)

Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs
by: Goel, Raghavv, et al.
Published: (2024)

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
by: Wei, Rongzhe, et al.
Published: (2025)

LRAGE: Legal Retrieval Augmented Generation Evaluation Tool
by: Park, Minhu, et al.
Published: (2025)

Show Your Work with Confidence: Confidence Bands for Tuning Curves
by: Lourie, Nicholas, et al.
Published: (2023)

Enhancing Automated Essay Scoring with Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training
by: Choi, Hongseok, et al.
Published: (2026)

Multicalibration for Confidence Scoring in LLMs
by: Detommaso, Gianluca, et al.
Published: (2024)

SteerConf: Steering LLMs for Confidence Elicitation
by: Zhou, Ziang, et al.
Published: (2025)

Single Character Perturbations Break LLM Alignment
by: Lin, Leon, et al.
Published: (2024)

On the Consideration of AI Openness: Can Good Intent Be Abused?
by: Kim, Yeeun, et al.
Published: (2024)

SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
by: Kirchhof, Michael, et al.
Published: (2025)

AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability
by: Agrawal, Sudhanshu, et al.
Published: (2024)

Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators
by: Mahaut, Matéo, et al.
Published: (2024)

The Confidence Trap: Gender Bias and Predictive Certainty in LLMs
by: Sabir, Ahmed, et al.
Published: (2026)

When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
by: Xiao, Yuxin, et al.
Published: (2025)

Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning
by: Zhang, Zhaowei, et al.
Published: (2026)

ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
by: Li, Chen, et al.
Published: (2026)

Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
by: Kumar, Abhishek, et al.
Published: (2024)

Confidence-Credibility Aware Weighted Ensembles of Small LLMs Outperform Large LLMs in Emotion Detection
by: Elgabry, Menna, et al.
Published: (2025)

MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools
by: Subramani, Nishant, et al.
Published: (2025)

Learning to Route LLMs with Confidence Tokens
by: Chuang, Yu-Neng, et al.
Published: (2024)

PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relations
by: Salimian, Sina, et al.
Published: (2025)

ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
by: Zhang, Bonan, et al.
Published: (2025)

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
by: Li, Pengyi, et al.
Published: (2025)

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

How Does Quantization Affect Multilingual LLMs?
by: Marchisio, Kelly, et al.
Published: (2024)

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
by: Giordani, Jeremiah
Published: (2025)

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning
by: Li, Guanlin, et al.
Published: (2025)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
by: Pan, Birong, et al.
Published: (2025)

Reasoning Boosts Opinion Alignment in LLMs
by: Berdoz, Frédéric, et al.
Published: (2026)

STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs
by: Dong, Peijie, et al.
Published: (2024)

How do LLMs Compute Verbal Confidence
by: Kumaran, Dharshan, et al.
Published: (2026)

House of Cards: Massive Weights in LLMs
by: Oh, Jaehoon, et al.
Published: (2024)

QEFT: Quantization for Efficient Fine-Tuning of LLMs
by: Lee, Changhun, et al.
Published: (2024)

Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs
by: Yang, Zhipeng, et al.
Published: (2025)

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
by: Diao, Muxi, et al.
Published: (2026)

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities
by: Sun, Chung-En, et al.
Published: (2024)

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
by: Kim, Jeonghye, et al.
Published: (2026)

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
by: Cha, Sungmin, et al.
Published: (2024)