Phoneme frequency distributions exhibit robust statistical regularities across languages, including exponential-tailed rank-frequency patterns and a negative relationship between phonemic inventory size and the relative entropy of the distribution. The origin of these patterns remains largely unexplained. In this paper, we investigate whether they can arise as consequences of the historical processes that shape phonological systems. We introduce a stochastic model of phonological change and simulate the diachronic evolution of phoneme inventories. A naïve version of the model reproduces the general shape of phoneme rank-frequency distributions but fails to capture other empirical properties. Extending the model with two additional assumptions –an effect related to frequency and a stabilising tendency toward a preferred inventory size– yields simulations that match both the observed distributions and the negative relationship between inventory size and relative entropy. These results suggest that some statistical regularities of phonological systems may arise as a result of diachronic sound change instead of –or in addition to– explicit optimisation or compensatory mechanisms.

Learning from interaction requires more than producing appropriate responses: learners must maintain a shared interaction with a partner, following its rules while adapting to feedback and contingencies. We argue that this depends on a prerequisite we call **protocol competence**: the ability to produce valid actions, maintain interaction structure, and respond appropriately across turns. In this paper, we investigate protocol competence in Small Language Models (SLMs) from the Qwen family across five interactive dialogue games from clembench, finding 51.3% of episodes from Qwen3.5-0.8B terminate in protocol violations. However, teacher demonstrations from a larger language model can scaffold participation, raising Wordle play from 0/30 to 29/30. Once models can reliably participate, we find self-improving reinforcement learning becomes effective: a single round of self-generated reinforcement learning (self-ReST) yields large gains from a small number of successful trajectories. Comparing adaptive learning strategies, we find that credit-weighted training provides the most reliable improvements, reducing variance relative to uniform supervision. Together, these results suggest that interactive learning follows a staged trajectory: SLMs must first acquire the competence to participate before they can exploit the contingencies generated by interaction.

Cross-lingual alignment in multilingual language models is typically attributed to joint training: shared parameters, mixed-language batches, or explicit alignment objectives. We ask whether monolingual models trained on non-parallel data learn alignable representations without joint training. By testing on strictly monolingual language models, such as the Goldfish model families and independently developed models from different research labs, we find three results. Correlation: these models develop alignable representational geometry across layers, with alignment strengthening as data scale, model scale, or linguistic proximity increases. Construction: a single Procrustes rotation fit on parallel sentences maps hidden states between models. Causation: the same rotation transfers functional content; patching a rotated English residual into a German model on a factual cloze flips the prediction to the donor’s capital in most cases. We confirm that cross-lingual alignment can emerge from the structure of language and the information it carries rather than from joint training, and this points to practical future directions including model stitching, merging, and modular multilingual systems built from monolingual components.

Bilingual language models (LMs) offer a controlled setting for studying how training conditions shape second-language (L2) behaviour, but prior work typically varies exposure structure, scale, and architecture at once, making it difficult to attribute effects to any single factor. We introduce **Beetle**, a controlled language model pretraining framework in which tokeniser, target language, training budget, and exposure structure are each independently manipulable, enabling systematic and comparable experimentation of training conditions. Using **Beetle**, we release 285 bilingual and 45 monolingual open-source LMs with rich checkpoints across a range of exposure schedules, data scales and first languages (L1s) to study multilingual pretraining and computational modelling of bilingualism and second language learning. Evaluating models on human bilingual and second language reading-time prediction and grammaticality judgement tasks, we find that staged and temporally structured curricula consistently improve alignment with language learner reading time compared to balanced bilingual training, with the largest gains at smaller data scales and for typologically closer language pairs. The **Beetle** models are well suited tools to help move computational psycholinguistics beyond its prevailing monolingual, English-centric focus toward models of human bilingual processing, to study cross-lingual learning dynamics, while supporting community-based development of controlled model families.

Language-specific tokenizers improve tokenization quality and the downstream performance of models on those languages. Using one with an existing pretrained model requires either training a new model from scratch or adapting the vocabulary of the pretrained one. We propose Language-adaptive Maximum a Posteriori (LangMAP) Tokenization, which extends the UnigramLM algorithm to the multilingual setting by replacing its single distribution over the vocabulary with one distribution per language over the same vocabulary. LangMAP can be used to train a multilingual language model from scratch, or to adapt a pretrained model’s tokenizer to individual languages without changing its vocabulary. Language labels are required to estimate the per-language distributions; at inference, the algorithm selects the highest-probability segmentation across languages, i.e., it does not need a language label. In experiments where we adapt a pretrained tokenizer with LangMAP, we observe that LangMAP’s new segmentation has consistently higher morphological boundary recall than the original tokenizer. In code data, it improves alignment with abstract syntax tree (AST) leaf boundaries in all configurations we try. Despite ostensible improvements in segmentations, in language model fine-tuning experiments, we do not observe significant differences in performance for most language-task pairs.

We present BabyBabelLM, a multilingual collection of datasets modeling the language a person observes from birth until they acquire a native language. We curate developmentally plausible pretraining data aiming to cover the equivalent of 100M English words of content in each of 45 languages. We compile evaluation suites and train baseline models in each language. BabyBabelLM aims to facilitate multilingual pretraining and cognitive modeling.

Language learners typically exhibit first language (L1) influence in their written second language (L2) production. We investigate whether similar patterns emerge in L2 language models (L2LMs), which are typically assessed on task-based benchmarks rather than on language use. We evaluate the use of Native Language Identification (NLI) as a method for detecting whether L2LMs exhibit human-like L1 influence. Using existing learner corpora and our novel L2 English dataset, we identify the conditions that yield the highest NLI accuracy, and show that text length but not proficiency affects performance. We then apply NLI to L2LM-generated text under various instruction-tuning and prompting conditions. We find that instruction tuning on human learner essays yields high NLI accuracy (~90%) and is necessary for detectable L1 influence. Whilst NLI accuracy is similar for L2LM and human essays, human evaluation shows that LM-generated L1 influence remains distinguishable from human writing.

Probing studies consistently find that language models (LMs) encode the truth of a statement along a low-dimensional linear direction of the residual stream. The Truth Co-occurrence Hypothesis (TCH) (Ravfogel et al., 2025) provides a mechanistic interpretation: tracking a latent truth variable is loss-reducing because true statements co-occur with true statements in natural text, evaluated using toy models and base LLMs. We replicate and extend the toy setting. In the tested fully trainable single-layer transformers, removing truth co-occurrence while preserving fact frequency eliminates linear truth decodability, supporting the necessity of co-occurrence in this setting. However, the same manipulation leaves the original toy model largely unchanged, revealing that probe-based evidence can arise from architectural artefacts rather than a functional truth-tracking mechanism. In pretrained Llama-3.1 models (8B and 70B), we reproduce the reported behavioural effect that false context reduces confidence in true facts, but show that nearly half of the original effect is explained by surface confounds. After controlling for these confounds, the effect remains robust across six factual relations. Under our probing protocol, cross-relation performance is closer to within-relation performance at 70B than at 8B. Our work characterises the emergence conditions for linear truth representations, and highlights the limitations of probe-based interpretability studies. Reproducibility Code is available here: https://github.com/Samzmc/truth-encoding-blackboxnlp26

The representation of grammatical knowledge in individual LLM neurons and attention heads remains poorly understood. We replicate the feature-based approach of Kryvosheieva et al. (2026) that uses functional localisation to illustrate that distinct syntactic phenomena can recruit the same units. We reproduce and extend the paper to new minimal pair datasets (Dutch, Turkish, and Russian) and additional interpretability techniques: Attention-based analysis, Differential Binary Masking (DBM), and Distributed Alignment Search (DAS). We find reproducible and robust evidence for syntactic localisation in LLMs across several methods and languages. However, localisation strength depends on interpretability techniques (particularly for DBM) and varies across languages, highlighting the value of validating mechanistic claims using several techniques. Code and data available via https://anonymous.4open.science/r/syntax-interpretability-F4C3

This report summarizes the findings from the 4th BabyLM Challenge. The BabyLM Challenge is a shared task aimed at closing the data-efficiency gap between human and machine language learners. This year, the challenge was held as part of the 2nd BabyLM Workshop. We kept the text-only (strict and strict-small) tracks from previous years; interaction-based systems (which previously had a separate track) were folded into these existing tracks. We also introduced a new multilingual track, where language models were required to perform well on BabyLM evaluations in English, Dutch, and Mandarin Chinese. We observe that GPT-BERT remains a strong architectural foundation for sample-efficient pre-training, and that more training epochs, recursion/looping, and data preprocessing are associated with stronger performance in general. The winning submissions to the new multilingual track additionally demonstrate that LLM-generated parallel data can be quite effective at improving multilingual capabilities in low-data settings.

Do independently trained monolingual language models converge on shared linguistic principles? To explore this question, we propose to analyze a suite of models trained separately on single languages but with identical architectures and budgets. We train sparse autoencoders (SAEs) on model activations to obtain interpretable latent features, then align them across languages using activation correlations. We do pairwise analyses to see if feature spaces show non-trivial convergence, and we identify universal features that consistently emerge across diverse models. Positive results will provide evidence that certain high-level regularities in language are rediscovered independently in machine learning systems.

Named-entity recognition (NER) in low-resource languages is usually tackled by finetuning very large multilingual LMs, an option that is often infeasible in memory- or latency-constrained settings. We ask whether small decoder LMs can be pretrained so that they adapt quickly and transfer zero-shot to languages unseen during pretraining. To this end we replace part of the autoregressive objective with first-order model-agnostic meta-learning (MAML). Tagalog and Cebuano are typologically similar yet structurally different in their actor/non-actor voice systems, and hence serve as a challenging test-bed. Across four model sizes (11 M – 570 M) MAML lifts zero-shot micro-F1 by 2–6 pp under head-only tuning and 1–3 pp after full tuning, while cutting convergence time by up to 8%. Gains are largest for single-token person entities that co-occur with Tagalog case particles si/ni, highlighting the importance of surface anchors.

Building language models (LMs), especially small and medium ones, remains more art than science. While large LMs often improve by sheer scale, it is still unclear why many design choices work. For small LMs, this uncertainty is more limiting: tight parameter budgets make each decision critical, yet researchers still lack systematic, scientific ways to test and refine new ideas. We introduce Pico, a lightweight, modular framework that enables systematic, hypothesis-driven research for small and medium-scale language model development. Pico consists of two libraries that together provide a practical sandbox where researchers can make targeted changes to a model’s architecture or training procedures and directly observe their effects on the model’s behavior. To support reproducible experimentation, we also release a suite of baseline models, pico-decoder, trained under standardized conditions and open-sourced for the community. Case studies highlight how Pico can support iterative small LM design and analysis.

Multi-turn dialogues between a child and caregiver are characterized by a property called contingency – prompt, direct, and meaningful exchanges between interlocutors. We introduce ContingentChat, a Teacher–Student framework that benchmarks and improves multi-turn contingency in a BabyLM trained on 100M words. Using a novel alignment dataset for post-training, BabyLM generates responses that are more grammatical and cohesive. Experiments with adaptive Teacher decoding strategies show limited additional gains. ContingentChat highlights the positive benefits of targeted post-training on dialogue quality and presents contingency as a challenging goal for BabyLMs.

Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information. Within the constraints of the Vision track for the BabyLM Challenge 2025, we propose a lightweight decoder-based architecture with (1) token-wise dynamic gating for adaptive fusion of linguistic and visual cues, (2) feature modulation and channel attention to maximise the utility of limited visual information and (3) auxiliary contrastive objectives for visual grounding. Evaluation on five benchmarks (BLiMP, BLiMP Supplement, EWoK, Winoground and VQA) shows competitive or superior performance to multimodal baselines. More notably, our dynamic gate discovers interpretable patterns without explicit supervision, favouring visual cues for content words and linguistic cues for function words. While we identify limitations in the Challenge constraints, such as the information bottleneck created by global image embeddings and training instability from the dataset split, our findings establish dynamic gating as a powerful tool for efficient multimodal learning, offering both interpretability and performance even under severe constraints.

Cross-lingual extensions of the BabyLM Shared Task beyond English incentivise the development of Small Language Models that simulate a much wider range of language acquisition scenarios, including code-switching, simultaneous and successive bilingualism and second language acquisition. However, to our knowledge, there is no benchmark of the formal competence of cognitively-inspired models of L2 acquisition, or L2LMs. To address this, we introduce a Benchmark of Learner Interlingual Syntactic Structure (BLiSS). BLiSS consists of 1.5M naturalistic minimal pairs dataset derived from errorful sentence–correction pairs in parallel learner corpora. These are systematic patterns –overlooked by standard benchmarks of the formal competence of Language Models – which we use to evaluate L2LMs trained in a variety of training regimes on specific properties of L2 learner language to provide a linguistically-motivated framework for controlled measure of the interlanguage competence of L2LMs.

Transformer language models typically operate with a fixed-length context window, which has grown in step with large-scale pretraining datasets. In the BabyLM Challenge, however, many past submissions have defaulted to using much shorter sequence lengths. We examine the impact of sequence length on BabyLM pretraining, to answer the simple question: what sequence length should we be using when training Baby LMs? Using 100M-word training data and fixed compute budgets, we compare 125M-parameter Mamba and OPT models, finding that although longer is often better, the optimal length depends on both task and architecture. Shorter sequences are sufficient for grammatical generalization tasks whereas longer contexts benefit morphological analogical reasoning tasks.

Curriculum Learning has been a popular strategy to improve the cognitive plausibility of Small-Scale Language Models (SSLMs) in the BabyLM Challenge. However, it has not led to considerable improvements over non-curriculum models. We assess whether theoretical linguistic acquisition theories can be used to specify more fine-grained curriculum learning strategies, creating age-ordered corpora of Child-Directed Speech for four typologically distant language families to implement SSLMs and acquisition-inspired curricula cross-lingually. Comparing the success of three objective curricula (Growing, Inwards & MMM) that precisely replicate the predictions of acquisition theories on a standard SSLM architecture, we find fine-grained acquisition-inspired curricula can outperform non-curriculum baselines and performance benefits of curricula strategies in SSLMs can be derived by specifying fine-grained language-specific curricula that precisely replicate language acquisition theories.