Language Model Self-Verification

Follow this topic Ask about this topic

Latest papers

17 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

On the Limits of Test-Time Compute for Self-Evaluation
Oct 30, 2026Anirudh Buvanesh, Khaled Rouissi, Sujin Yun +6Language Model Self-Assessment Language Model Self-Verification
Mila · Université de Montréal · Nous Research +3
Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models
Sep 3, 2026Syed Ghazanfar Abbas, Dongyan XuLLM Security Language Model Auditing
Purdue University
Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models
Aug 19, 2026Wei Yu, Suxing Liu, Minjie Yu +4Language Model Self-Verification LLM Self-Refinement
School of Digital Arts, Jiangxi Arts & Ceramics Technology Institute, Jingdezhen 33001, China · School of Computing, Universiti Sains Malaysia, 11800 USM Penang, Malaysia
Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B
Jul 30, 2026Iliya MirzaeiLanguage Model Self-Assessment LLM Self-Refinement
Department of Computer Science Stony Brook University
SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute
Jul 30, 2026Hongyu Chen, Liang Lin, Guangrun WangLanguage Model Self-Verification RL for Language Model Reasoning
1Sun Yat-sen University · 2Guangdong Key Laboratory of Big Data Analysis and Processing · 3X-Era AI Lab
Exploring Extrinsic and Intrinsic Properties for Effective Reasoning with Code Interpreter
Jun 15, 2026Patomporn Payoungkhamdee, Napat Laosaengpha, Jenta Wonglertsakul +8Language Model Self-Verification LLM Reasoning
Vidyasirimedhi Institute of Science and Technology · Kasetsart University · SCB 10X +4
Score $\times$ Decoder: A Unified View of Unsupervised Inference-Time Scaling for Hallucination Mitigation
May 30, 2026Yun-Chen Cheng, Che-Yu Lin, Cheng-Lin YangLanguage Model Self-Verification Language Model Decoding
CyCraft AI Lab, Taiwan
FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning
May 27, 2026Haihui Pan, Junwei Bao, Hongfei Jiang +1Language Model Self-Verification LLM Answer Verification
Zuoyebang Education Technology
Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline
May 20, 2026Tony Lee, Percy LiangLanguage Model Self-Verification Self-Training for Language Models
Stanford University
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
Apr 16, 2026Kiran Purohit, Ramasuri Narayanam, Soumyabrata PalLanguage Model Self-Verification LLM Answer Verification
IIT Kharagpur · Adobe Research
When Should a Language Model Trust Itself? Same-Model Self-Verification as a Conditional Confidence Signal
Apr 8, 2026Aditya Ajay PhalodLanguage Model Self-Verification Language Model Self-Assessment
Independent Researcher
SAGE Celer 2.6 Technical Card
Mar 24, 2026SAGEA Research Team, Basab Jha, Firoj Paudel +8Language Model Self-Verification Multilingual Language Models
SAGEA · Tribhuwan University | Vedas College · Tribhuwan University | Madan Bhandari Memorial College +2
A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement
Mar 20, 2026Yuran Li, Di Wu, Benoit BouletLanguage Model Self-Verification Language Model Self-Improvement
Department of Electrical and Computer Engineering, McGill University · Department of Mechanical, Industrial and Aerospace Engineering, Concordia University
CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
Mar 18, 2026Teng Pan, Yuchen Yan, Zixuan Wang +6Language Model Self-Verification RL for Language Model Reasoning
Zhejiang University · Baidu Inc.
Decoding the Critique Mechanism in Large Reasoning Models
Mar 17, 2026Hoang Phan, Quang H. Nguyen, Hung T. Q. Le +3Language Model Self-Verification Large Reasoning Models
VinUni-Illinois Smart Health Center, VinUniversity · University of Illinois Urbana-Champaign
$V_1$ : Unifying Generation and Self-Verification for Parallel Reasoners
Mar 4, 2026Harman Singh, Xiuyu Li, Kusha Sareen +14Language Model Self-Verification Test-Time Scaling
UC Berkeley · Mila · Together AI +1
Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
Feb 18, 2026Xingyu Dang, Rohit Agarwal, Rodrigo Porto +3Language Model Self-Verification Mathematical Reasoning
Princeton University · Princeton Language and Intelligence

Oct 30, 2026J/K move · Enter open · S save

On the Limits of Test-Time Compute for Self-Evaluation

Anirudh Buvanesh, Khaled Rouissi, Sujin Yun, Johan Obando-Ceron+5

Mila · Université de Montréal · Nous Research+3

Language Model Self-Assessment Language Model Self-Verification Test-Time Scaling LLM Reranking Algorithmic Reasoning

Open paper AskPDF arXiv

Self-verification and aggregation have emerged as popular approaches for bridging the gap between pass@1 and pass@N. However, increasing the number of candidates does not consistently narrow the gap between final-answer accuracy and pass@N. To understand this limitation, we use ranking error to measure how reliably models distinguish their correct generations from incorrect ones. We show that ranking error admits a bias-variance decomposition, with both components shaped by algorithmic design choices and inference compute. Across our experiments, additional compute reduces variance, while bias initially decreases before approaching a plateau. Guided by this analysis, we introduce Scorpio, a simple and general method that jointly scores randomly grouped candidates. Across math, code, and puzzle benchmarks, Scorpio improves verification, tree search, and aggregation. For verification, Scorpio improves accuracy over the strongest baseline by up to 7 percentage points while matching or exceeding that baseline's peak accuracy with 17-42% lower inference cost. For tree search, using Scorpio to score partial solutions and select the final answer improves accuracy by up to 10 percentage points over prior methods. Finally, Scorpio improves the scaling of aggregation-based methods by 11 percentage points on coding tasks.