AutoPSV: Automated Process-Supervised Verifier

• URL: http://arxiv.org/abs/2405.16802v4
• Date: Thu, 24 Oct 2024 09:52:59 GMT
• Title: AutoPSV: Automated Process-Supervised Verifier
• Authors: Jianqiao Lu, Zhiyang Dou, Hongru Wang, Zeyu Cao, Jianbo Dai, Yingjia Wan, Zhijiang Guo,
• Abstract summary: textbfAutomated textbfProcess-textbfSupervised textbfVerifier (textbftextscAutoPSV) textscAutoPSV begins by training a verification model on the correctness of final answers. We experimentally validate that the step-level confidence changes learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps.
• Score: 10.283965168399158
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we propose a novel method named \textbf{Auto}mated \textbf{P}rocess-\textbf{S}upervised \textbf{V}erifier (\textbf{\textsc{AutoPSV}}) to enhance the reasoning capabilities of large language models (LLMs) by automatically annotating the reasoning steps. \textsc{AutoPSV} begins by training a verification model on the correctness of final answers, enabling it to generate automatic process annotations. This verification model assigns a confidence score to each reasoning step, indicating the probability of arriving at the correct final answer from that point onward. We detect relative changes in the verification's confidence scores across reasoning steps to automatically annotate the reasoning process, enabling error detection even in scenarios where ground truth answers are unavailable. This alleviates the need for numerous manual annotations or the high computational costs associated with model-induced annotation approaches. We experimentally validate that the step-level confidence changes learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps. We demonstrate that the verification model, when trained on process annotations generated by \textsc{AutoPSV}, exhibits improved performance in selecting correct answers from multiple LLM-generated outputs. Notably, we achieve substantial improvements across five datasets in mathematics and commonsense reasoning. The source code of \textsc{AutoPSV} is available at \url{https://github.com/rookie-joe/AutoPSV}.

Related papers

• Incentivizing LLMs to Self-Verify Their Answers [20.2584779107763]
  Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks.<n>We propose a framework that incentivizes LLMs to self-verify their own answers.<n>We train our self-verification models based on Qwen2.5-Math-7B and DeepSeek-R1-Distill-Qwen-1.5B.
  arXiv  Detail & Related papers  (2025-06-02T06:54:29Z)
• Can Large Reasoning Models Self-Train? [58.953117118687096]
  Scaling the performance of large language models increasingly depends on methods that reduce reliance on human supervision.<n>We propose an online self-training reinforcement learning algorithm that leverages the model's self-consistency to infer correctness signals and train without any ground-truth supervision.
  arXiv  Detail & Related papers  (2025-05-27T17:16:00Z)
• The Geometry of Self-Verification in a Task-Specific Reasoning Model [45.669264589017665]
  We train a model using DeepSeek R1's recipe on the CountDown task. We do a top-down and bottom-up analysis to reverse-engineer how the model verifies its outputs.
  arXiv  Detail & Related papers  (2025-04-19T18:40:51Z)
• Adaptive Rectification Sampling for Test-Time Compute Scaling [5.085583751997239]
  We propose Adaptive Rectification Sampling (AR-Sampling) to guide large language models to self-correction.<n>Our approach enables the models to rethink in more fine-grained level, improving the accuracy of solutions.
  arXiv  Detail & Related papers  (2025-04-02T02:57:52Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models. Our framework incorporates two complementary strategies: internal TTC and external TTC. We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving [17.289776394847063]
  We propose a novel verifier-in-the-loop design for Automatic Theorem Proving task. We empirically show that the step-by-step local verification produces a global improvement in the model's reasoning accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-03-12T18:20:47Z)
• Debiased Prompt Tuning in Vision-Language Model without Annotations [14.811475313694041]
  Vision-Language Models (VLMs) may suffer from the problem of spurious correlations.<n>By leveraging pseudo-spurious attribute annotations, we propose a method to automatically adjust the training weights of different groups.<n>Our approach efficiently improves the worst-group accuracy on CelebA, Waterbirds, and MetaShift datasets.
  arXiv  Detail & Related papers  (2025-03-11T12:24:54Z)
• Self-Adaptive Paraphrasing and Preference Learning for Improved Claim Verifiability [9.088303226909277]
  In fact-checking, structure and phrasing of claims critically influence a model's ability to predict verdicts accurately. We propose a self-adaptive approach to extract claims that is not reliant on labeled training data. We show that this novel setup extracts a claim paraphrase that is more verifiable than their original social media formulations.
  arXiv  Detail & Related papers  (2024-12-16T10:54:57Z)
• Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Prompting [0.0]
  We present a large language model (LLM) -based flow to automatically generate high-quality SystemVerilog Assertions (SVA) We introduce a novel sub-task-focused fine-tuning approach, leading to a remarkable 7.3-fold increase in the number of functionally correct assertions. Experiments demonstrate a 26% increase in the number of assertions free from syntax errors using this approach.
  arXiv  Detail & Related papers  (2024-11-23T03:52:32Z)
• InstructAV: Instruction Fine-tuning Large Language Models for Authorship Verification [9.151489275560413]
  This paper introduces a novel approach, termed InstructAV, for authorship verification. This approach utilizes LLMs in conjunction with a parameter-efficient fine-tuning (PEFT) method to simultaneously improve accuracy and explainability.
  arXiv  Detail & Related papers  (2024-07-16T16:27:01Z)
• Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models [54.14602121129874]
  We introduce AutoIF, the first scalable and reliable method for automatically generating instruction-following training data. AutoIF transforms the validation of instruction-following data quality into code verification.
  arXiv  Detail & Related papers  (2024-06-19T13:29:53Z)
• A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains [33.46649770312231]
  Prompting language models to provide step-by-step answers is a prominent approach for complex reasoning tasks. No fine-grained step-level datasets are available to enable thorough evaluation of such verification methods. We introduce REVEAL: Reasoning Verification Evaluation, a dataset to benchmark automatic verifiers of complex Chain-of-Thought reasoning.
  arXiv  Detail & Related papers  (2024-02-01T12:46:45Z)
• Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability [58.582216812183496]
  Language models (LMs) can sometimes generate factually correct text and estimate truth values of individual claims. Current LMs generate incorrect or nonsensical content, and are difficult to edit and bring up to date. We present a method called Deductive Closure Training (DCT) that uses LMs themselves to identify implications of (and contradictions within) the text that they generate.
  arXiv  Detail & Related papers  (2024-01-16T18:58:37Z)
• Uncertainty-aware Language Modeling for Selective Question Answering [107.47864420630923]
  We present an automatic large language model (LLM) conversion approach that produces uncertainty-aware LLMs. Our approach is model- and data-agnostic, is computationally-efficient, and does not rely on external models or systems.
  arXiv  Detail & Related papers  (2023-11-26T22:47:54Z)
• Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers [121.53749383203792]
  We present a holistic end-to-end solution for annotating the factuality of large language models (LLMs)-generated responses. We construct an open-domain document-level factuality benchmark in three-level granularity: claim, sentence and document. Preliminary experiments show that FacTool, FactScore and Perplexity are struggling to identify false claims.
  arXiv  Detail & Related papers  (2023-11-15T14:41:57Z)
• Autoencoding Variational Autoencoder [56.05008520271406]
  We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency. We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
  arXiv  Detail & Related papers  (2020-12-07T14:16:14Z)
• Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
  Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
  arXiv  Detail & Related papers  (2020-04-29T10:54:40Z)
• Generating Fact Checking Explanations [52.879658637466605]
  A crucial piece of the puzzle that is still missing is to understand how to automate the most elaborate part of the process. This paper provides the first study of how these explanations can be generated automatically based on available claim context. Our results indicate that optimising both objectives at the same time, rather than training them separately, improves the performance of a fact checking system.
  arXiv  Detail & Related papers  (2020-04-13T05:23:25Z)
• Model Assertions for Monitoring and Improving ML Models [26.90089824436192]
  We propose a new abstraction, model assertions, that adapts the classical use of program assertions as a way to monitor and improve ML models. Model assertions are arbitrary functions over a model's input and output that indicate when errors may be occurring. We propose methods of using model assertions at all stages of ML system deployment, including runtime monitoring, validating labels, and continuously improving ML models.
  arXiv  Detail & Related papers  (2020-03-03T17:49:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.