The following papers were recommended by the Semantic Scholar API
\n- \n
- TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model (2025) \n
- Fromto: Multidimensional Supervision of Reasoning Process for LLM Optimization (2025) \n
- Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math (2025) \n
- GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling for Step-Level Reasoning (2025) \n
- Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey (2025) \n
- Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning (2025) \n
- Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning (2025) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads
Abstract
Transformer-based uncertainty quantification heads improve step-level reasoning verification in LLMs by estimating uncertainty from internal states, offering a lightweight and scalable alternative to existing methods.
Solving complex tasks usually requires LLMs to generate long multi-step reasoning chains. Previous work has shown that verifying the correctness of individual reasoning steps can further improve the performance and efficiency of LLMs on such tasks and enhance solution interpretability. However, existing verification approaches, such as Process Reward Models (PRMs), are either computationally expensive, limited to specific domains, or require large-scale human or model-generated annotations. Thus, we propose a lightweight alternative for step-level reasoning verification based on data-driven uncertainty scores. We train transformer-based uncertainty quantification heads (UHeads) that use the internal states of a frozen LLM to estimate the uncertainty of its reasoning steps during generation. The approach is fully automatic: target labels are generated either by another larger LLM (e.g., DeepSeek R1) or in a self-supervised manner by the original model itself. UHeads are both effective and lightweight, containing less than 10M parameters. Across multiple domains, including mathematics, planning, and general knowledge question answering, they match or even surpass the performance of PRMs that are up to 810x larger. Our findings suggest that the internal states of LLMs encode their uncertainty and can serve as reliable signals for reasoning verification, offering a promising direction toward scalable and generalizable introspective LLMs.
Community
Solving complex tasks usually requires LLMs to generate long multi-step reasoning chains. Previous work has shown that verifying the correctness of individual reasoning steps can further improve the performance and efficiency of LLMs on such tasks and enhance solution interpretability. However, existing verification approaches, such as Process Reward Models (PRMs), are either computationally expensive, limited to specific domains, or require large-scale human or model-generated annotations. Thus, we propose a lightweight alternative for steplevel reasoning verification based on data-driven uncertainty estimation. We train transformer-based uncertainty quantification heads (UHeads) that use the internal states of the frozen LLM to estimate the uncertainty of its reasoning steps during generation. The approach is fully automatic: target labels are generated either by another larger LLM (e.g., DeepSeek R1) or in a self-supervised manner by the original model itself. UHeads are both effective and lightweight, containing less than 10M parameters. Across multiple domains, including mathematics, planning, and general knowledge question answering, they match or even exceed the performance of PRMs that are up to 810× larger. Our findings suggest that the internal states of LLMs encode their uncertainty and can serve as reliable signals for reasoning verification, offering a promising direction towards scalable and generalizable introspective LLMs.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model (2025)
- Fromto: Multidimensional Supervision of Reasoning Process for LLM Optimization (2025)
- Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math (2025)
- GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling for Step-Level Reasoning (2025)
- Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey (2025)
- Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning (2025)
- Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper