Copertina

VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Petullo, James, George, Sonny, Cashman, Dylan, Xue, Nianwen
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
di: Petullo, James, et al.
Pubblicazione: (2026)

Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction
di: George, Sonny, et al.
Pubblicazione: (2024)

Confidence Improves Self-Consistency in LLMs
di: Taubenfeld, Amir, et al.
Pubblicazione: (2025)

Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning
di: Oh, Jungsuk, et al.
Pubblicazione: (2025)

The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure
di: Li, Yubo, et al.
Pubblicazione: (2026)

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
di: Chen, Haoyang, et al.
Pubblicazione: (2026)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
di: Wang, Changsheng, et al.
Pubblicazione: (2025)

Maximizing Confidence Alone Improves Reasoning
di: Prabhudesai, Mihir, et al.
Pubblicazione: (2025)

Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces
di: Pathak, Manas, et al.
Pubblicazione: (2026)

Reasoning or Fluency? Dissecting Probabilistic Confidence in Best-of-N Selection
di: Kim, Hojin, et al.
Pubblicazione: (2026)

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
di: Li, Yiwei, et al.
Pubblicazione: (2025)

Tiny-QMoE
di: Cashman, Jack, et al.
Pubblicazione: (2025)

Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation
di: Lee, Jaehyeok, et al.
Pubblicazione: (2024)

Improving Score Reliability of Multiple Choice Benchmarks with Consistency Evaluation and Altered Answer Choices
di: Cavalin, Paulo, et al.
Pubblicazione: (2025)

Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction
di: Zeng, Qinglin, et al.
Pubblicazione: (2025)

MPN: Leveraging Multilingual Patch Neuron for Cross-lingual Model Editing
di: Si, Nianwen, et al.
Pubblicazione: (2024)

A Generalised Approach for Encoding and Reasoning with Qualitative Theories in Answer Set Programming
di: Baryannis, George, et al.
Pubblicazione: (2020)

Does Inference Scaling Improve Reasoning Faithfulness? A Multi-Model Analysis of Self-Consistency Tradeoffs
di: Mehta, Deep
Pubblicazione: (2026)

The Shape of Reasoning: Topological Analysis of Reasoning Traces in Large Language Models
di: Tan, Xue Wen, et al.
Pubblicazione: (2025)

PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains
di: Leang, Joshua Ong Jun, et al.
Pubblicazione: (2025)

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction
di: Zhang, Chen, et al.
Pubblicazione: (2026)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces
di: He, Chen, et al.
Pubblicazione: (2026)

Roundtable Policy: Confidence-Weighted-Consensus Aggregation Improves Multi-Agent-System Reasoning
di: Yao, Yu, et al.
Pubblicazione: (2025)

Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models
di: Zhou, Xin, et al.
Pubblicazione: (2025)

Self-Consistency Boosts Calibration for Math Reasoning
di: Wang, Ante, et al.
Pubblicazione: (2024)

FANS -- Formal Answer Selection for Natural Language Math Reasoning Using Lean4
di: Yao, Jiarui, et al.
Pubblicazione: (2025)

ReasonOps: Operator Segmentation for LLM Reasoning Traces
di: Lee, Daniel, et al.
Pubblicazione: (2026)

Predicting Winning Captions for Weekly New Yorker Comics
di: Cao, Stanley, et al.
Pubblicazione: (2024)

Reasoning about Study Regulations in Answer Set Programming
di: Hahn, Susana, et al.
Pubblicazione: (2024)

Plantain: Plan-Answer Interleaved Reasoning
di: Liang, Anthony, et al.
Pubblicazione: (2025)

CASK: Core-Aware Selective KV Compression for Reasoning Traces
di: Kim, Buseong, et al.
Pubblicazione: (2026)

Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
di: Huang, Jingkai, et al.
Pubblicazione: (2026)

Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
di: Bhambri, Siddhant, et al.
Pubblicazione: (2025)

Beyond Self-Consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging
di: Chang, Chia-Hsuan, et al.
Pubblicazione: (2024)

Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
di: Kim, Seungwook, et al.
Pubblicazione: (2026)

Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling
di: Wan, Guangya, et al.
Pubblicazione: (2024)

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
di: Zhuang, Ziqing, et al.
Pubblicazione: (2026)

Incentivizing LLMs to Self-Verify Their Answers
di: Zhang, Fuxiang, et al.
Pubblicazione: (2025)

Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision
di: Jang, Chaeyun, et al.
Pubblicazione: (2025)