5arXiv cs.CL (Computation and Language)·
Large-scale study of uncertainty estimation across 22 languages in LLMs finds English reasoning improves low-resource UE
A new arXiv preprint presents the first large-scale evaluation of uncertainty estimation (UE) methods across 22 languages, covering high-, mid-, and low-resource settings using nine open- and closed-box UE methods. Key findings include that prompting models to reason in English while keeping questions in low-resource languages substantially improves UE performance, suggesting the reliability bottleneck is in generation rather than comprehension. The study also finds that optimal UE method choice depends on model scale: probability-based open-box methods win at smaller scales, while self-verbalized closed-box uncertainty dominates at larger scales. Practical guidance on threshold selection for abstention in multilingual settings is also provided.
Related guides (1)
Related events (8)
Three-axis uncertainty estimation framework for code generation outperforms NL-derived baselines
A new arXiv preprint argues that uncertainty estimation (UE) for code generation requires code-specific design rather than methods ported from natural language. The authors propose three orthogonal uncertainty axes—lexical (token entropy), algorithmic (pseudo-code consistency), and functional (behavioral consistency)—grounded in properties unique to code: token fragility, intent-code gap, and executability. Evaluated across five code LLMs, their ensemble improves average AUROC from 0.696 to 0.776 (+8.1 points) over the strongest NL-derived baseline, with a single-pass token entropy method on Qwen3-14B matching multi-pass baselines at 3x lower cost. The work is directly relevant to safe deployment of LLMs in agentic coding pipelines.
Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study
This paper systematically investigates strategies for extending LLM-based automatic evaluation (LLMs-as-a-Judge) to multilingual settings, covering high-, mid-, and low-resource languages (English, Spanish, Basque). The authors compare instruction translation, monolingual vs. multilingual supervision, and model size, finding that fine-tuned smaller models can match proprietary models when in-domain data is available, while zero-shot larger models are preferable out-of-domain. Two meta-evaluation datasets are extended to Spanish and Basque, and all data and code are publicly released.
Luar: Selective Translation via Reinforcement Learning for Multilingual Reasoning
Luar is a reinforcement learning framework that trains reasoning language models to selectively invoke English translation only when direct understanding of a non-English input is deemed unreliable. The approach, built on top of GRPO, outperforms standard multilingual baselines across reasoning benchmarks, with especially large gains on low-resource languages. Analysis confirms the model learns to avoid unnecessary translation when direct reasoning suffices, and generalizes the translation-call behavior to unseen low-resource languages.
Study finds local languages provide better cultural knowledge access in LLMs once proficiency is controlled
A new arXiv paper introduces a controlled evaluation framework to disentangle language proficiency from culture-specific knowledge access in LLMs. Using real-world cultural questions across 13 locales and ~80 models, the authors apply item response theory to show that while English dominates on culture-agnostic questions, local languages yield a consistent knowledge-access advantage on culture-specific questions once proficiency differences are factored out. The finding challenges the common interpretation that weaker local-language accuracy implies weaker cultural knowledge, and has implications for how multilingual and regionally-aligned models are evaluated.
Reverse Probing: Supervised Token-level Uncertainty Quantification for LLMs in Clinical Text
The paper introduces Reverse Probing, a novel uncertainty quantification framework designed specifically for clinical text summarization that estimates token-level uncertainty from pre-existing labeled summaries rather than sampling new outputs. It extracts uncertainty signals from four categories of internal model activations, treating text as a probe into the model's internal state. Evaluated on two expert-annotated clinical datasets, it outperforms eight adapted baselines on all metrics, achieving up to 4× higher AUPRC while reducing inference time and compute. Feature analysis identifies delta energy and neighborhood context as the most consistent predictors of uncertainty across models.
Systematic Study of LLM Linguistic Uncertainty Markers and Intrinsic Confidence Calibration
This paper introduces 'marker internal confidence' (MIC) as a formalization of the intrinsic confidence a model associates with epistemic markers (e.g., 'it is likely...') in a given task domain. The authors present 7 metrics to evaluate MIC stability within and across distributions, finding that LLMs remain miscalibrated even under model-centric interpretation of marker meanings. Models struggle to differentiate markers by internal confidence across distributions, though they preserve a somewhat consistent ranking order across tasks. The work provides complementary evidence toward understanding faithful calibration in LLMs and highlights the need for more stable, aligned marker use.
Tracing the Emergence of Human-Like Pragmatic Reasoning in LLMs Across Languages
Researchers conducted a population-matching experiment evaluating 25 LLMs on conditional inference tasks across four languages, comparing model behavior to matched human populations. The study finds that LLMs function as accurate semantic operators but systematically fail to capture pragmatic enrichments—context-sensitive inferences beyond literal logical meaning—that humans apply effortlessly. Model performance on pragmatic reasoning is not predicted by open vs. closed weights, training orientation, or architecture type, suggesting pragmatic reasoning remains an emergent and unreliable capability. The findings contribute to ongoing debates about whether LLMs reason like humans or merely approximate surface-level linguistic patterns.
Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
This paper investigates uncertainty quantification (UQ) for activation oracles—systems that make LLM internal activations human-legible—by evaluating 6 confidence estimation methods across 6,000 samples per oracle. The authors find that bootstrap mode frequency achieves the best calibration (ECE 5.7% vs. 25.5% for log-probability baseline on Qwen3-8B), while the log-prob baseline remains useful as a cheap triage signal. Experiments vary verbalizer and context prompts across two Qwen3 model sizes. Code and a patched trainer are released publicly.