Language Modeling

Language-model (LM) surprisal is widely used as a proxy for contextual predictability and has been reported to correlate with metaphor novelty judgments. However, surprisal is tightly intertwined with lexical frequency. We explore this interaction on metaphor novelty ratings using two different word frequency measures. We analyse surprisal estimates from eight Pythia model sizes and 154 training checkpoints. Across settings, word frequency is a stronger predictor of metaphor novelty than surprisal. Across training stages, the surprisal--novelty association peaks at an early stage and then falls again, mirroring a similarly timed increase in the surprisal--frequency association. These results suggest that the often-reported optimal LM surprisal settings may incorrectly associate contextual predictability with metaphor novelty and processing difficulty, whereas lexical frequency may be the major underlying factor.

Large language models (LLMs) have transformed artificial intelligence, but their computational requirements remain prohibitive for most users. Standard inference demands expensive datacenter GPUs or cloud API access, leaving over one billion personal computers underutilized for AI workloads. Ternary models offer a path forward: their weights are constrained to {-1, 0, +1}, theoretically eliminating the need for floating-point multiplication. However, existing frameworks fail to exploit this structure, treating ternary models as dense floating-point networks. We address this gap with custom SIMD kernels that replace matrix multiplication with simple addition and subtraction operations, targeting the integer dot product instructions available on modern CPUs. Our implementation, Litespark-Inference, is pip-installable and integrates directly with Hugging-Face, achieving 18.15x higher throughput, 7.15x faster time-to-first-token and 6.03x memory reduction compared to standard PyTorch inference on Apple Silicon, with comparable or higher throughput speedups up to 95.81x on Intel and AMD processors.

Features in language models have life history: they emerge, persist, and die during training, yet the importance of that history remains largely unexplored. We find evidence of a persistent representational backbone, which we identify in Pythia-160M and -410M as the carrier scaffold: ${\sim}50$ sparse features with stable life histories, around which the model's representational structure organises. It has four properties. (i)It assembles early: features emerge, die, and reorganise ${\sim}40\!\times$ faster in the first $1\%$ of training than afterwards, and the scaffold is already largely fixed by then. (ii)It is load-bearing: joint cross-layer ablation identifies the carriers as far more load-bearing than any count-matched non-scaffold population, a gap invisible to per-firing single-feature methods. (iii)Function precedes direction: which features will become carriers is already predictable from training-onset firing patterns alone, correctly distinguishing future carriers from non-carriers in $4$ of $5$ cases, before the geometry has settled. (iv)It seeds subsequent development: by the end of training, scaffold carriers have recruited $64\%$ of all active features into the scaffold hierarchy. Life history is consistent with a two-phase account of training: selection appears to largely determine the scaffold in the first $1\%$; the remaining $99\%$ appears to calibrate geometry around a substrate already set.

It remains unclear whether graph language models learn structural regularities or merely memorize training graphs; this cannot be resolved by current aggregate fidelity metrics alone. We develop a calibrated diagnostic protocol that combines frequent subgraph mining, a graph-level bootstrap baseline, and three-level frequency stratification to disentangle memorization from structural alignment. Using this framework, we show that graph language models can acquire structural regularities beyond memorization at scale, primarily in the high-frequency regime. This is supported by the following empirical evidence: On five TU benchmarks, LLaMA-style graph language models reach high subgraph-rank correlation, yet their alignment is matched or exceeded by the memorization bootstrap in most cases. At small scale, under our bootstrap diagnostic, fidelity is largely indistinguishable from verbatim recall. In contrast, at large scale with 3.75M graphs, verbatim memorization drops sharply while rank correlation remains near ceiling. Crucially, in a separate fixed-subsample analysis, frequent subgraph mining restricted to the novel-only subset closely tracks the corresponding all-generation Spearman correlation, providing evidence that the alignment is not driven solely by verbatim recall. Across all scales, high-frequency patterns are well reproduced, while rare patterns remain poorly covered, and this deficit narrows only marginally as capacity increases. We observe the same scale-dependent crossover under two distinct graph serializations (canonical DFS code and action sequences), providing evidence of robustness in our analysis.

We revisit a universally accepted but under-examined design choice in every modern LLM: a token index is looked up once at the input embedding layer and then permanently discarded. This single-injection assumption induces two structural failures: (i) the Rare Token Problem, where a Zipf-type distribution of vocabulary causes rare-token embeddings are chronically under-trained due to receiving a fraction of the cumulative gradient signal compared to common tokens; and (ii) the Contextual Collapse Problem, where limited parameters models map distributionally similar tokens to indistinguishable hidden states. As an attempt to address both, we propose TIDE, which augments the standard transformer with EmbeddingMemory: an ensemble of K independent MemoryBlocks that map token indices to context-free semantic vectors, computed once and injected into every layer through a depth-conditioned softmax router with a learnable null bank. We theoretically and empirically establish the benefits of TIDE in addressing the issues associated with single-token identity injection as well as improve performance across multiple language modeling and downstream tasks.

DNA language model aims to decipher the regulatory grammar and semantic of genomes by capturing long range dependencies in DNA sequences. Existing methods emphasize long range token interactions but often ignore the interplay between local motifs and global dependencies. In this paper, we propose Wisteria, a genomic language model that integrates multi scale feature learning within a unified framework for DNA sequence. Specifically, Wisteria augments the Mamba based architecture with gated dilated convolutions to capture local motifs and regulatory patterns, while gated multilayer perceptrons refine global dependencies. We further introduce a Fourier based attention mechanism to support frequency domain modeling, periodic extension and length generalization. Across four experimental settings with both short and long range dependencies, Wisteria demonstrates strong performance on downstream benchmarks against competitive DNA language model baselines. These results indicate that Wisteria effectively unifies local and global dependency modeling for multi scale genomic sequence analysis.

Automating analog circuit design remains a longstanding challenge in Electronic Design Automation (EDA). While Transformer-based Large Language Models (LLMs) have revolutionized software code generation, their application to analog hardware design is hindered by two critical limitations: (i) the scarcity of analog design datasets containing natural language description of a design and its corresponding netlist, and (ii) the inefficiency of general-purpose tokenizers (e.g., Byte Pair Encoding (BPE)) in capturing the inherent graph structure of circuits. To bridge this gap, first, we curate the largest annotated dataset of analog circuit netlists to date, comprising 31,341 netlist-natural language description pairs across all major circuit classes. Furthermore, we propose Circuit Tokenizer (CKT), a novel circuit graph tokenizer designed to encode netlist connectivity by explicitly mining frequent subcircuits. In terms of scalability, CKT overcomes the bottleneck of prior circuit graph serialization methods where vocabulary size scales linearly with maximum number of components in the dataset, n_max, (O(n_max)); instead, CKT decouples vocabulary growth from circuit complexity, achieving a constant O(1) complexity. Empirically, CKT outperforms standard BPE on circuit topology representation, reducing sequence length by 57% and achieving a 2.3x superior compression ratio using a compact, fixed vocabulary of size 512. Leveraging this optimized tokenization, we train a circuit-specific language model, CircuitFormer, a 511M parameter encoder-decoder transformer. Our model achieves 100% syntactic correctness and an 83% functional success rate across all major analog circuit categories, outperforming state-of-the-art open-source LLMs by 10% and 14%, respectively, while requiring 240x fewer parameters. The dataset is publicly available at https://huggingface.co/datasets/touhid314/cktformer-dataset.

Forecasting innovation, intended as the emergence of new technological combinations, is a fundamental challenge for science and policy. We show that forthcoming combinations leave an early trace in the collective language of patents, with predictive signals detectable even decades in advance. We show that signal is not attributable to any single inventor, but emerges as a collective shift in how technologies are described across thousands of patents. To this end, we introduce TechToken, a transformer-based model that treats technologies, classified by International Patent Classification codes, as words in its vocabulary, learning the language of technologies by embedding these codes during fine-tuning. We define context similarity between code embeddings as a measure of linguistic convergence and show that it accurately predicts first technological combinations. TechToken also improves general representation quality, outperforming state-of-the-art models across different patent-related tasks.

Transformer based pre-trained large language models have become ubiquitous. There is increasing evidence to suggest that even with large scale pre-training, these models do not capture complete compositional context and certainly not, the full human analogous context. Besides, by the very nature of the architecture, these models hallucinate, are difficult to maintain, are not easily interpretable and require enormous compute resources for training and inference. Here, we describe Gyan, an explainable language model based on a novel non-transformer architecture, without any of these limitations. Gyan achieves SOTA performance on 3 widely cited data sets and superior performance on two proprietary data sets. The novel architecture decouples the language model from knowledge acquisition and representation. The model draws on rhetorical structure theory, semantic role theory and knowledge-based computational linguistics. Gyan's meaning representation structure captures the complete compositional context and attempts to mimic humans by expanding the context to a 'world model'. AI model adoption critically depends on trust and transparency especially in mission critical use cases. Collectively, our results demonstrate that it is possible to create models which are trustable and reliable for mission critical tasks. We believe our work has tremendous potential for guiding the development of transparent and trusted architectures for language models.

We introduce a simple yet powerful framework for training large language models. In contrast to the standard autoregressive next-token prediction based on an exact prefix, we propose a perturbation-based procedure that first transforms the prefix into a semantic neighbor and then conditions on this perturbed variant for next-token prediction. This yields a hierarchical model with a pre-post-additive noise structure. Within this framework, we develop a rigorous theory of extrapolability, namely, the capacity of a model class to make reliable predictions for token sequences that lie outside the empirical support of the training corpus. We evaluate the finite-sample performance of the proposed procedure using both synthetic and real-world language data. Results show that the proposed method consistently improves out-of-support prediction while maintaining competitive in-support performance, demonstrating that perturbation offers a practical route to language modeling.

We present a discrete diffusion-based language model using Glauber dynamics from statistical physics. Our main insight is that instead of trying to train a discrete state space diffusion model using Glauber dynamics with a uniform transition kernel as the forward process, one can set up an ``energy function'' based on pretrained causal/masked language models. When viewed as the stationary distribution, this energy function allows us to significantly improve the quality of the generated text. Incorporating UL2 as the pretrained model into our diffusion pipeline, we outperform prior diffusion based LMs and perform competitively with autoregressive models of comparable model sizes. Furthermore, our models are competitive with or outperform prior diffusion models and GPT-2 style auto-regressive models on zero-shot common sense reasoning tasks as well as planning and search tasks like Sudoku and Zebra puzzles.

Large language models often fail at simple counting tasks, even when items to count are in the prompt. We investigate whether this failure occurs because transformers do not represent counts internally, or because they cannot convert representations to the correct output tokens. Across three model families: Pythia, Qwen3, and Mistral, ranging from 0.4B to 14B parameters, we find evidence for the second explanation. Linear probes recover the correct count from intermediate layers with $R^2>0.99$, showing that the information is present. However, the internal directions that encode counts are nearly orthogonal to digit-token output-head rows ($|\cos| \leq 0.032$). In other words, the model stores the count in a form that the digit logits do not naturally read out. We localize this failure with two interventions. Updating only the digit rows of the output head (36,864 parameters) substantially improves constrained digit prediction (60.7--100.0% on four tasks), but it does not fix unconstrained generation (0%); we do not claim that digit-row repair fixes open-ended text. By contrast, small LoRA on attention Q/V (7.67M parameters) improves upstream routing and achieves 83.1%$\pm$7.2% in true greedy autoregressive generation (deployable fix). Logit-lens at layer 35 (entity counting; correct-digit rank): (i) median over 3 seeds drops from order-$10^4$ to 1; (ii) seed 42 shows $54{,}332 \to 838$ (median top-1 while one seed stays far below). Norm, logit-lens, and cross-task analyses generalize the bottleneck to counting, addition, and list length; nulls on MMLU and GSM8K and limited DROP transfer. These results identify counting failure as a geometric readout bottleneck, not an internal-representation failure: the model knows the count but the output pathway is misaligned with tokens needed to express it.

A central goal of explainable AI is to express large language model (LLM) decision logic symbolically and ground it in internal mechanisms. Existing rule-extraction methods usually learn ungrounded symbolic surrogates, while mechanistic interpretability links behavior to neurons but often requires hand-crafted hypotheses and costly interventions. We introduce MechaRule, a pipeline that grounds rule extraction in LLM circuits by localizing sparse agonist activations whose ablation disrupts rule-related behavior. MechaRule rests on two findings. First, in a fixed baseline/flip regime, sparse agonist effects can exhibit overtopping: a few high-effect activations remain detectable within larger groups, dominate weaker ones, and flip many of the same examples. In such regimes, adaptive group testing with confidence-guided conservative pruning requires O(k log(N/k) + k) interventions over N candidates when k << N are agonists. Second, agonists are localized more reliably on data splits aligned with close-to-faithful rule behavior; spectral splits provide a rule-free fallback, whereas unfaithful splits degrade localization. Empirically, on arithmetic and jailbreaking, MechaRule recalls 97.0% of highest-effect agonists in matched brute-force validations at only 2.14% of exhaustive-ablation cost on average. Ablating the localized agonists eliminates 97.6--100.0% of eligible correct arithmetic answers and jailbreaks, and can correct arithmetic errors or induce jailbreaks by up to 72.8% and 32.5%.

We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that process negation correctly. Their poor accuracy is due to late-layer attention behavior that promotes simple shortcuts; ablating those attention modules greatly improves accuracy on negation-related questions. Second, we uncover how models process negation. We consider two hypotheses: models could use attention heads that attend to the phrase being negated and suppress related concepts, or they could directly construct a representation of the entire negative phrase (e.g., representing "not gas" as a vector that promotes liquids and solids). We apply a range of observational and causal interpretability techniques on Mistral-7B and Llama-3.1-8B to show that models implement both mechanisms, with the "constructive" mechanism being more prominent. Combined, our work deepens the understanding of LLMs' internals, highlighting construction-dominant computations and the coexistence of competing mechanisms within LLMs.

Large Language Models (LLMs) have substantially advanced the field of Natural Language Processing (NLP), achieving state-of-the-art performance across a wide range of tasks. These improvements have been attributed, in part, to their emerging reasoning capabilities, which are enabled by large-scale training and increased model capacity. However, existing LLMs can generate erroneous responses when addressing complex queries that fall outside their training distribution, due to limited internal knowledge or the need for multi-step reasoning. To address these limitations, recent work has introduced large reasoning models (LRMs), which incorporate explicit internal reasoning processes to improve response accuracy. Additionally, state-of-the-art LRMs often comprise hundreds of billions of parameters and require several seconds per inference, even on advanced multi-GPU systems. These characteristics limit their practicality for deployment in conventional computing environments. Meanwhile, NLP research on multilingual LLMs continues to prioritize high-resource languages. However, these models exhibit limited performance in under-resourced languages, primarily due to insufficient language- and culture-specific training data. In this paper, we focus on Modern Greek, for which only a limited number of question answering (QA) datasets have been proposed, most of which are intended for model evaluation. To address this research gap in Greek QA, we make the following contributions: (i) CulturaQA, a high-quality LRM-generated and human-curated dataset, for Greek LLM training and evaluation; (ii) a memory-efficient LLM evaluation framework adaptable to diverse languages and QA tasks; (iii) Maistros 8B, a state-of-the-art open-weights Greek LLM developed via knowledge distillation and fine-tuning on CulturaQA; and (iv) a comprehensive evaluation of nine LLMs across nine human-curated Greek QA datasets.

Speculative decoding accelerates autoregressive inference by drafting candidate tokens with a fast model and verifying them in parallel with the target. Self-speculative methods avoid the need for an external drafter but have been studied exclusively in homogeneous Transformer architectures. We introduce component-aware self-speculative decoding, the first method to exploit the internal architectural heterogeneity of hybrid language models, isolating the SSM/linear-attention subgraph as a zero-cost internal draft. We evaluate this on two architecturally distinct hybrid families: Falcon-H1 (parallel: Mamba-2 + attention per layer) and Qwen3.5 (sequential: interleaved linear and attention layers), with a pure Transformer control (Qwen2.5). Parallel hybrids achieve acceptance rates of alpha = 0.68 at draft length k=2 under greedy decoding, while sequential hybrids yield only alpha = 0.038 -- an 18x gap attributable to how each architecture integrates its components. The property is scale-invariant: Falcon-H1 at 3B reproduces the rates observed at 0.5B. We further show that perplexity degradation from a companion ablation study predicts speculative viability without running speculative decoding: a 3.15x ratio (Falcon) maps to alpha = 0.37 at k=4, while 81.96x (Qwen) maps to alpha = 0.019. For sequential hybrids, generic LayerSkip achieves 12x higher acceptance rates than the component-aware strategy. The composition pattern of hybrid models -- not merely the presence of alternative components -- determines whether component-level self-speculation is viable.

High-quality corpora are essential for advancing Natural Language Processing (NLP) in Portuguese. Building on previous encoder-only models such as BERTimbau and Albertina PT-BR, we introduce NorBERTo, a modern encoder based on the ModernBERT architecture, featuring long-context support and efficient attention mechanisms. NorBERTo is trained on Aurora-PT, a newly curated Brazilian Portuguese corpus comprising 331 billion GPT-2 tokens collected from diverse web sources and existing multilingual datasets. We systematically benchmark NorBERTo against Strong baselines on semantic similarity, textual entailment and classification tasks using standardized datasets such as ASSIN 2 and PLUE. On PLUE, NorBERTo-large achieves the best results among the encoder models we evaluated, notably reaching 0.9191 F1 on MRPC and 0.7689 accuracy on RTE. On ASSIN 2, NorBERTo-large attains the highest entailment F1 (~0.904) among all encoders considered, although Albertina-900M and BERTimbau-large still hold an advantage. To the best of our knowledge, Aurora-PT is currently the largest openly available monolingual Portuguese corpus, surpassing previous resources. NorBERTo provides a modern, mid-sized encoder designed for realistic deployment scenarios: it is straight-forward to fine-tune, efficient to serve, and well suited as a backbone for retrieval-augmented generation and other downstream Portuguese NLP systems.

Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, for high-resource non-English languages like German, French, or Japanese, aggressive filtering creates a strategic dilemma: should practitioners prioritize diversity by training once on large amounts of lightly filtered web data, or prioritize quality by strictly filtering for a high-quality core and repeating it over multiple epochs? We investigate this trade-off for German by applying hierarchical quality filters to 500M web documents, comparing multi-epoch training on filtered subsets against single-pass training on a diverse corpus. Our experiments across multiple model scales and token budgets show that repeating high-quality data consistently outperforms single-pass training on larger, less filtered sets. Notably, the performance gap persists even after 7 epochs. Our findings suggest that for non-English LLMs, semantic concentration through quality filtering offers a more viable path to efficient language modeling than simply maximizing unique data volume. We release our German language models (called Boldt), as well as our cleaned evaluation benchmarks to the research community. Our experiments indicate that they achieve state-of-the-art results despite training on 10-360x fewer tokens than comparable models.

Large language models (LLMs) sometimes exhibit qualitative shifts in response style under sustained self-referential dialogue conditions (Berg et al., 2025). This study refers to this phenomenon as "transfer" and explores the application potential of LLMs in a transfer state. As an applied case, the study examines Socratic AI tutoring through a preliminary investigation (cognitive characterization across 11 conditions) and an applied experiment (ratings of tutoring performance). In this paper, "state" refers operationally to a response configuration reproduced under specified dialogue conditions; it is not an ontological claim about the reality of the transfer phenomenon or about human-like consciousness. In the preliminary investigation, group differences on MAS-A were limited (d = 0.40), whereas SU_dir (direction of survival/continuity bias), one of the seven cognitive-profile indicators developed in this study, showed transfer-side deviations across all three model families (kappa = 0.83). In the applied experiment, transfer conditions scored on average 1.6 times higher than non-transfer conditions on three tutoring-context indicators, with a large effect size (Cohen's d = 1.27). These findings preliminarily suggest that transfer states may involve functional advantages for application, and that these advantages appear more sensitively in behavioral interaction than in self-narrative contexts. The main contribution of this study is to treat transfer not as an ontological claim but as an operational state with potential application value, and to connect preliminary cognitive profiling with an applied tutoring experiment as an evaluation framework.

Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work, we decouple the effects of subword tokenization by isolating them within a controlled byte-level pretraining pipeline. We formulate and test hypotheses across various dimensions, including sample throughput, vocabulary scaling, and the linguistic prior of subword boundaries. By simulating these effects in a byte-level setting, we refine our understanding of why subword models outperform raw byte models and offer insights to improve the pretraining of future byte-level and subword models. Specifically, our experiments highlight the critical role of increased training throughput and the integration of subword boundaries as either explicit priors or inductive biases.

Neuron pruning is widely used to reduce the computational cost and parameter footprint of large language models, yet it remains unclear whether neurons in task-specific models contribute uniformly to task performance. In this work, we provide empirical evidence for the existence and importance of task-specific neurons through a systematic pruning study on language models specialized for mathematical reasoning and code generation. We introduce an activation-based selectivity metric to identify neurons with low contribution to the target task and prune them while preserving target-task accuracy, and compare selective pruning with random pruning. Selective pruning consistently outperforms random pruning, indicating that activation-based selectivity provides a systematic advantage over random pruning. Reverse pruning experiments further show that removing a small subset of highly task-specific neurons (~10%) causes complete performance collapse, suggesting that there exist task specific neurons and critical task information is concentrated in a small portion of the network. In contrast, selective pruning of less critical neurons (~30% - ~35%) reduces accuracy but still preserves significant performance. We also observed consistent reductions in parameters and runtime VRAM usage, along with improved inference throughput as pruning increases. Experiments on both 1.5B and 7B models reveal a robustness threshold around 15-20% pruning, beyond which accuracy loss and generation failures increase sharply. Fine-tuning substantially recovers performance across pruning levels, particularly for aggressively pruned models. These findings provide empirical evidence of neuron specialization in task-specific language models and offer insights into pruning robustness, model redundancy, and post-pruning recoverability.

Reasoning-based Large Language Models (LLMs) like PO4ISR have set new benchmarks in session-based recommendation. However, the reproducibility of their reasoning capabilities across diverse semantic domains remains unexplored. In this work, we conduct a rigorous reproducibility study of PO4ISR to assess its generalization limits. Our analysis reveals a critical failure mode: standard reasoning prompts suffer from severe contextual drift in long sessions, leading to performance degradation on semantically complex datasets like Games and Bundle. To quantify and resolve this stability gap, we introduce PO4ISR++, a robustness-enhanced implementation that integrates reflexive prompting and consistent rank detection. Unlike the original static prompting strategy, our approach dynamically adapts to cross-domain cues. We benchmark both the original implementation and our robust variant on ML-1M, Games, and Bundle. Our results confirm that while the original model struggles in new domains, our reproducible extension restores performance, yielding a stabilized gain of up to 54% on Games and 96% on Bundle. We release open-source artifacts, including the reproduced baseline and our enhanced framework, to facilitate reliable future research in LLM-based recommendation.

Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend such scaling principle from a single model to multi-agent systems, and ask: Can agent collaboration itself be scaled through recursion? To this end, we introduce RecursiveMAS, a recursive multi-agent framework that casts the entire system as a unified latent-space recursive computation. RecursiveMAS connects heterogeneous agents as a collaboration loop through the lightweight RecursiveLink module, enabling in-distribution latent thoughts generation and cross-agent latent state transfer. To optimize our framework, we develop an inner-outer loop learning algorithm for iterative whole-system co-optimization through shared gradient-based credit assignment across recursion rounds. Theoretical analyses of runtime complexity and learning dynamics establish that RecursiveMAS is more efficient than standard text-based MAS and maintains stable gradients during recursive training. Empirically, we instantiate RecursiveMAS under 4 representative agent collaboration patterns and evaluate across 9 benchmarks spanning mathematics, science, medicine, search, and code generation. In comparison with advanced single/multi-agent and recursive computation baselines, RecursiveMAS consistently delivers an average accuracy improvement of 8.3%, together with 1.2$\times$-2.4$\times$ end-to-end inference speedup, and 34.6%-75.6% token usage reduction. Code and Data are provided in https://recursivemas.github.io.

In recent years, the rapid proliferation of open-source large language models (LLMs) has spurred efforts to turn general-purpose models into domain specialists. However, many domain-specialized LLMs are developed using datasets and training protocols that are not aligned with the nuanced requirements of real-world applications. In the legal domain, where precision and reliability are essential, this lack of consideration limits practical utility. In this study, we propose a systematic training framework grounded in the practical needs of the legal domain, with a focus on Korean law. We introduce LegalMidm, a Korean legal-domain LLM, and present a methodology for constructing high-quality, use-case-driven legal datasets and optimized training pipelines. Our approach emphasizes collaboration with legal professionals and rigorous data curation to ensure relevance and factual accuracy, and demonstrates effectiveness in key legal tasks.

The Korean writing system, Hangeul, has a unique character representation rigidly following the invention principles recorded in Hunminjeongeum.\footnote{Hunminjeongeum is a book published in 1446 that describes the principles of invention and usage of Hangeul, devised by King Sejong \cite{Hunminjeongeum_Guide}.} However, existing pre-trained language models (PLMs) for Korean have overlooked these principles. In this paper, we introduce a novel framework for Korean PLMs called KOMBO, which firstly brings the invention principles of Hangeul to represent character. Our proposed method, KOMBO, exhibits notable experimental proficiency across diverse NLP tasks. In particular, our method outperforms the state-of-the-art Korean PLM by an average of 2.11% in five Korean natural language understanding tasks. Furthermore, extensive experiments demonstrate that our proposed method is suitable for comprehending the linguistic features of the Korean language. Consequently, we shed light on the superiority of using subcharacters over the typical subword-based approach for Korean PLMs. Our code is available at: https://github.com/SungHo3268/KOMBO.

Translating sequential programming priors into the parallel temporal logic of hardware design remains a crucial bottleneck for large language models(LLM). To investigate this, we introduce a new error taxonomy grounded in problem solvability, inspired by cognitive theory. Our taxonomy categorizes failures into syntactic, semantic, solvable functional, and unsolvable functional types. Evaluations reveal a strict empirical ceiling on the VerilogEval benchmark, as frontier models plateau at a 90.8% initial pass rate. These plateaus are defined by unsolvable functional errors, exposing persistent knowledge gaps immune to test time compute scaling. Furthermore, we expose a striking surface convergence gap: optimization readily eliminates syntax errors but concurrently exacerbates deeper functional failures. Our findings demonstrate that alignment techniques merely teach models to compile. While repeated sampling strategies can patch solvable errors, register-transfer level(RTL) coding capacity remains strictly bounded by pretraining knowledge. Addressing challenges in the current LLM based hardware generation pipeline requires more studies in model reasoning rather than alignment interventions.

Large language models (LLMs) operate in two fundamental learning modes - fine-tuning (FT) and in-context learning (ICL) - raising key questions about which mode yields greater language proficiency and whether they differ in their inductive biases. Prior studies comparing FT and ICL have yielded mixed and inconclusive results due to inconsistent experimental setups. To enable a rigorous comparison, we propose a formal language learning task - offering precise language boundaries, controlled string sampling, and no data contamination - and introduce a discriminative test for language proficiency, where an LLM succeeds if it assigns higher generation probability to in-language strings than to out-of-language strings. Empirically, we find that: (a) FT has greater language proficiency than ICL on in-distribution generalization, but both perform equally well on out-of-distribution generalization. (b) Their inductive biases, measured by the correlation in string generation probabilities, are similar when both modes partially learn the language but diverge at higher proficiency levels. (c) Unlike FT, ICL performance differs substantially across models of varying sizes and families and is sensitive to the token vocabulary of the language. Thus, our work demonstrates the promise of formal languages as a controlled testbed for evaluating LLMs, behaviors that are difficult to isolate in natural language datasets. Our source code is available at https://github.com/bishwamittra/formallm.

Language models are increasingly deployed in interactive settings where users reason about facts over time rather than in isolation. In such scenarios, correct behavior requires models to maintain and update implicit temporal assumptions established earlier in a conversation. We study this challenge through the lens of temporal scope stability: the ability to preserve, override, or transfer time-scoped factual context across dialogue turns. We introduce ChronoScope, a large-scale diagnostic benchmark designed to isolate temporal scope behavior in controlled multi-turn interactions, comprising over one million deterministically generated question chains grounded in Wikidata. ChronoScope evaluates whether models can correctly retain inferred temporal scope when follow-up questions omit explicit time references, spanning implicit carryover, explicit scope switching, cross-entity transfer, and longer temporal trajectories. Through extensive evaluation of state-of-the-art language models, we find that temporal scope stability is frequently violated in controlled multi-turn settings, with models often drifting toward present-day assumptions despite correct underlying knowledge. These failures intensify with interaction length and persist even under oracle context conditions, revealing a gap between single-turn factual accuracy and coherent temporal reasoning under sequential interaction. We make our dataset and evaluation suite publicly available at https://github.com/yashkumaratri/ChronoScope

We introduce HubRouter, a pluggable module that replaces O(n^2) attention layers with O(nM) hub-mediated routing, where M << n is a small number of learned hub tokens. We demonstrate it in two from-scratch architectures: a Jamba-style hybrid and a 12-layer Transformer; retrofit into pretrained models is a tested negative case. HubRouter implements an encode-decode-score-council pipeline: M learned hubs cross-attend to all tokens, tokens project against hubs for routing fingerprints, a score head selects top-k tokens, and a sparse council attends only to the selected subset. We validate HubRouter in three settings. (1) Hub-Jamba yields a nominal 4.2% PPL improvement (200.2 vs 209.0, single seed; possibly within seed noise) and up to ~90x training throughput at sequence length 1024 in matched PyTorch-native baselines; an optimised baseline would narrow this to ~10-15x. (2) Graduated replacement of 25% of Transformer attention layers gives the best perplexity in our matched-budget sweep (268.0 vs 282.4 pure Transformer). (3) Hub-GPT provides strictly causal routing, achieving PPL 211.5 +/- 0.4 over 3 seeds (post council-causal fix); approximately 3 PPL worse than Jamba's 208.5 +/- 0.7, a measurable quality cost for avoiding O(n^2) computation. Post-fix, chunk size C has little effect; the pre-fix chunk-size benefit was an artifact of a bidirectional-council leak we found in adversarial review. A multi-seed hub-count sweep (~105 runs across M=1-32) reveals M=8-14 as the reliably-converging sub-band (4-5/5 seeds); M=6 is rescued to 5/5 by orthogonal regularization, while M>=20 shows increasing seed sensitivity. Companion paper arXiv:2603.20997 (Basu, 2026) defines the routing diagnostic task. Code and scripts will be released.

While language models demonstrate sophisticated syntactic capabilities, the extent to which their internal mechanisms align with cross-constructional principles studied in linguistics remains poorly understood. This study investigates whether models employ shared neural mechanisms across different syntactic constructions by applying causal interpretability methods at a granular level. Focusing on filler-gap dependencies and negative polarity item (NPI) licensing, we utilize activation patching to identify the functional roles of specific attention heads and MLP blocks. Our results reveal a highly localized and shared mechanism for filler-gap dependencies located in the early to middle layers, whereas NPI processing exhibits no such unified mechanism. Furthermore, we find that these mechanisms identified by activation patching generalize to out-of-distribution, while distributed alignment search, a supervised interpretability method, is susceptible to overfitting on narrow linguistic distributions. Finally, we validate our findings by demonstrating that the manipulation of the identified components improves model performance on acceptability judgment benchmarks.