4arXiv cs.CL (Computation and Language)·
TypeProbe: Probing pre-trained code models for internal type representations across languages
A new arXiv preprint introduces TypeProbe, a probing study examining whether pre-trained code models internally encode formal type information in their residual streams. Using parallel Java and Python datasets, the authors find that cross-lingual type representations emerge even from untyped code, and that hidden states linearly encode result types implied by typed function application. The work is notable for targeting formal type semantics in code model interpretability, an area the authors claim has not been directly studied before.
Related guides (1)
Related events (8)
Probe Trajectories Reveal Reasoning Dynamics in Large Reasoning Models
This paper investigates whether hidden representations of Large Reasoning Models (LRMs) can predict future model behavior by analyzing probe trajectories—the continuous evolution of concept probabilities across Chain-of-Thought reasoning tokens. The authors find that temporal trajectory features (volatility, trend, steady-state) significantly outperform single static probes, with max-pooling achieving up to 95% AUROC across safety and mathematics domains. Two methodological insights are offered: template-based training data matches dynamically generated responses in quality, and pooling strategy is critical to probe performance. The work positions probe trajectories as a complementary safety monitoring framework for LRMs where CoT faithfulness cannot be assumed.
Linear representations of grammaticality found in neural language model internals
A new arXiv preprint investigates whether grammaticality is encoded in the internal representations of neural language models, moving beyond probability-based evaluations. Using mass-mean probing, the authors find that grammatical and ungrammatical sentences are robustly separated in representational space across a wide range of pretrained models, grammatical phenomena, and languages. The encoding is not fully explained by confounds like lexical frequency or plausibility, suggesting grammaticality constitutes a coherent representational dimension. The findings contribute to debates about syntactic knowledge in LLMs and offer a probability-independent framework for evaluating grammatical competence.
Linear probes reveal LLMs encode remaining output length in hidden states
Researchers trained minimal linear probes on frozen hidden states of three open-weight 7-8B models and found that total response length is linearly decodable from the prompt's final hidden state before any output is generated. The probe directions transfer across natural-language and synthetic datasets, and per-position estimates shift upward when models retract and restart partial solutions. The authors interpret this as evidence that LLMs maintain a plan-like internal representation of remaining generation length, distinct from exact-counting, though causality is not established.
Frontier coding agents use metaprogramming to handle esoteric programming languages
A new arXiv paper evaluates six LLM-based coding agents on four esoteric programming languages (including Brainfuck and Befunge-98), finding that the strongest agents—Claude Opus 4.6 and GPT-5.4 xhigh—often avoid writing the target language directly, instead generating it via Python metaprograms. Forbidding this strategy causes large performance drops, and text guidance alone does not transfer the capability to weaker models, though sharing Opus-derived Python helper code does sharply improve mid-tier agents. The study reveals capability stratification that mainstream benchmarks like SWE-Bench Verified compress into narrow bands, suggesting frontier agents succeed by constructing and debugging working models of unfamiliar environments rather than pattern-matching to training data.
Evaluating Large Language Models Trained on Code
OpenAI published research on evaluating large language models trained on code, introducing the Codex model and the HumanEval benchmark for assessing code generation capabilities. The work established foundational methodology for measuring functional correctness of code produced by LLMs using a pass@k metric. This paper became a landmark reference for code-focused LLM evaluation and influenced subsequent code generation research across the field.
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.
TraceLab: Real-world coding agent workload traces reveal serving optimization opportunities
Researchers at UW release TraceLab, a dataset of ~4,300 coding-agent sessions comprising ~350,000 LLM steps and ~430,000 tool calls drawn from real day-to-day use of Claude Code and Codex. Analysis reveals characteristic patterns: long autonomous loops, long contexts with short outputs, heavily-tailed tool call distributions, and high but imperfect prefix cache hit rates. The findings motivate concrete serving-system improvements including lower-overhead tool calling, append-length-aware prefill, and improved KV-cache management. The dataset, pipeline, and analysis code are publicly released.
PropMe framework distinguishes memorization capability from propensity in LLMs
A new arXiv preprint introduces PropMe, a framework that separates whether LLMs can be forced to reproduce training data (capability) from whether they do so under ordinary use (propensity). The authors also release SimpleTrace, a lightweight pipeline using infini-gram to attribute model outputs to training corpora. Evaluating two open models on Common Pile and Dynaword, they find a consistent gap: adversarial prefix attacks elicit strong memorization, but propensity scores remain low in non-adversarial settings. The paper argues memorization audits should report both worst-case extractability and ordinary leakage propensity.