Copertina

Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jang, Chaeyun, Choi, Moonseok, Kim, Yegon, Lee, Hyungi, Lee, Juho
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
di: Jang, Chaeyun, et al.
Pubblicazione: (2024)

Parallel Test-Time Scaling with Multi-Sequence Verifiers
di: Kim, Yegon, et al.
Pubblicazione: (2026)

Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models
di: Kim, Mingyeong, et al.
Pubblicazione: (2026)

Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
di: Choi, Moonseok, et al.
Pubblicazione: (2023)

Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation
di: Jang, Chaeyun, et al.
Pubblicazione: (2024)

A Model-Free Universal AI
di: Kim, Yegon, et al.
Pubblicazione: (2026)

Mitigating Legibility Tax with Decoupled Prover-Verifier Games
di: Kim, Yegon, et al.
Pubblicazione: (2026)

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models
di: Kim, Sanghyun, et al.
Pubblicazione: (2024)

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
di: Yoon, Kanghoon, et al.
Pubblicazione: (2025)

Confidence-guided Refinement Reasoning for Zero-shot Question Answering
di: Jang, Youwon, et al.
Pubblicazione: (2025)

Calibrating Verbalized Confidence with Self-Generated Distractors
di: Wang, Victor, et al.
Pubblicazione: (2025)

Reasoning Models Better Express Their Confidence
di: Yoon, Dongkeun, et al.
Pubblicazione: (2025)

Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts
di: Kim, Hyunsu, et al.
Pubblicazione: (2024)

Dimension Agnostic Neural Processes
di: Lee, Hyungi, et al.
Pubblicazione: (2025)

Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion
di: Kim, Sanghyun, et al.
Pubblicazione: (2024)

Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records
di: Kwon, Yeonsu, et al.
Pubblicazione: (2026)

Process Supervision via Verbal Critique Improves Reasoning in Large Language Models
di: Chen, Hao-Yuan
Pubblicazione: (2026)

Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech
di: Woo, Sang Hoon, et al.
Pubblicazione: (2025)

Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
di: Leong, Chak Tou, et al.
Pubblicazione: (2026)

PILOT-Bench: A Benchmark for Legal Reasoning in the Patent Domain with IRAC-Aligned Classification Tasks
di: Jang, Yehoon, et al.
Pubblicazione: (2026)

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

ConfTuner: Training Large Language Models to Express Their Confidence Verbally
di: Li, Yibo, et al.
Pubblicazione: (2025)

ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification
di: Liu, Siran, et al.
Pubblicazione: (2026)

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
di: Shi, Dachuan, et al.
Pubblicazione: (2025)

From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs
di: Wang, Shaojie, et al.
Pubblicazione: (2026)

Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback
di: Potamitis, Nearchos, et al.
Pubblicazione: (2025)

Semiparametric Token-Sequence Co-Supervision
di: Lee, Hyunji, et al.
Pubblicazione: (2024)

AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
di: Koh, Woosung, et al.
Pubblicazione: (2025)

Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
di: Kim, San, et al.
Pubblicazione: (2026)

LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations
di: Zhang, Caiqi, et al.
Pubblicazione: (2025)

PACR: Progressively Ascending Confidence Reward for LLM Reasoning
di: Yoon, Eunseop, et al.
Pubblicazione: (2025)

Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
di: Lee, Wonjun, et al.
Pubblicazione: (2026)

The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
di: Kim, Dueun, et al.
Pubblicazione: (2026)

Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
di: Lu, Yuyin, et al.
Pubblicazione: (2026)

EXAONE Deep: Reasoning Enhanced Language Models
di: Bae, Kyunghoon, et al.
Pubblicazione: (2025)

Evalet: Evaluating Large Language Models through Functional Fragmentation
di: Kim, Tae Soo, et al.
Pubblicazione: (2025)

Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Triplet Extraction
di: Lai, Wenna, et al.
Pubblicazione: (2026)

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
di: Zhang, Yunxiang, et al.
Pubblicazione: (2025)

Self-Supervised Learning Based Handwriting Verification
di: Chauhan, Mihir, et al.
Pubblicazione: (2024)

Do LLMs Need Inherent Reasoning Before Reinforcement Learning? A Study in Korean Self-Correction
di: Kim, Hongjin, et al.
Pubblicazione: (2026)