Using Semantic Distance to Estimate Uncertainty in LLM-Based Code Generation

• URL: http://arxiv.org/abs/2605.09023v1
• Date: Sat, 09 May 2026 16:02:54 GMT
• Title: Using Semantic Distance to Estimate Uncertainty in LLM-Based Code Generation
• Abstract summary: LLMs show strong performance in code generation, but their outputs lack correctness guarantees.<n>We introduce a taxonomy that disentangles these choices and reveals a missing design point: semantic distance-aware uncertainty estimation.<n>Our metrics provide strong proxies for correctness, and consistently outperform state-of-the-art sample-based baselines.
• Score: 1.1470070927586018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLMs show strong performance in code generation, but their outputs lack correctness guarantees. Sample-based uncertainty estimators address this by generating multiple candidate programs and measuring their disagreement. However, existing estimators make different design choices about how behaviours are identified, aggregated, referenced and compared, making them difficult to assess. We therefore first introduce a taxonomy that disentangles these choices and reveals a missing design point: semantic distance-aware uncertainty estimation, which measures not only whether sampled programs disagree, but how severely their execution behaviours differ. Across LiveCodeBench, MBPP, HumanEval-X and BigCodeBench, spanning Python, Java and C++, our metrics provide strong proxies for correctness, and consistently outperform state-of-the-art sample-based baselines across both closed-source models (GPT-3.5-Turbo, GPT-4o-mini, Gemini-2.5-Flash-Lite, Claude Opus 4.5) and an open-source model (DeepSeek-Coder-V2). The method is practical: it requires neither model internals nor LLM-as-judge calls, remains robust across models, languages, sampling temperatures and fuzzing settings, and reduces runtime by approximately 48-79% relative to existing baselines.

Related papers

• Evaluating Language Models on Cross-Language Code Functional Equivalence [6.76025470599609]
  We introduce PolyHuman, a dataset of human-written programs in CPP, Java, and Python.<n>Using this dataset, we evaluate intra- and inter-language equivalence detection across open-weight and proprietary LLMs.<n>We analyze 81 cases of systematic disagreement in which models incorrectly judge functional equivalence.
  arXiv  Detail & Related papers  (2026-08-25T01:41:00Z)
• Latent Performance Profiling of Large Language Models [47.009623327601226]
  We introduce Latent Performance Profiling (LPP) -- a framework that derives task-agnostic diagnostics from hidden activations and output distributions.<n>Unlike static accuracy scores, LPP provides stable, architecture-sensitive signatures across models of similar size.<n>We show that models with similar benchmark scores can exhibit contrasting latent profiles, such as differences in entropy or adaptability.
  arXiv  Detail & Related papers  (2026-05-28T14:41:26Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• Ensemble-Based Uncertainty Estimation for Code Correctness Estimation [36.53771380869671]
  We propose Ensemble Semantic Entropy (ESE), which estimates uncertainty by evaluating the consistency of samples aggregated across an ensemble of models.<n>Experiments on LiveCodeBench demonstrate that ESE correlates more strongly with program correctness than single-model semantic entropy.<n>We also propose a cascading test-time scaling framework Cas, which maintains performance while reducing FLOPs by 64.9% compared to single-model scaling.
  arXiv  Detail & Related papers  (2026-03-28T02:37:36Z)
• Robust Search with Uncertainty-Aware Value Models for Language Model Reasoning [31.973976155760397]
  Value model guided search is effective in steering LLM generation but suffers from a lack of robustness.<n>We propose an uncertainty-aware framework with two key components: (1) Uncertainty-Aware Value Models (UVMs), which replace single-point value estimates with value distributions to quantify prediction reliability, and (2) Group Thompson Sampling, an efficient algorithm that selects candidates based on their probability of being optimal.
  arXiv  Detail & Related papers  (2025-02-16T15:10:30Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access [5.922444371605447]
  This study aims to address the pervasive challenge of quantifying uncertainty in large language models (LLMs) without logit-access. Existing Conformal Prediction (CP) methods for LLMs typically assume access to the logits, which are unavailable for some API-only LLMs. We introduce a novel CP method that is tailored for API-only LLMs without logit-access; (2) minimizes the size of prediction sets; and (3) ensures a statistical guarantee of the user-defined coverage.
  arXiv  Detail & Related papers  (2024-03-02T14:14:45Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

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.