Fresh from the feed

arXiv:2511.12768v1 Announce Type: new Abstract: Phase transitions have been proposed as the origin of emergent abilities in large language models (LLMs), where new capabilities appear abruptly once models surpass critical thresholds of scale. Prior work, such as that of Wei et al., demonstrated these phenomena under model and data scaling, with transitions revealed after applying a log scale to training compute. In this work, we ask three complementary questions: (1) Are phase transitions unique to large models, or can they also be observed in small transformer-based language models? (2) Can such transitions be detected directly in linear training space, rather than only after log rescaling? and (3) Can these transitions emerge at early stages of training? To investigate, we train a small GPT-style transformer on a character-level corpus and analyze the evolution of vocabulary usage throughout training. We track the average word length, the number of correct versus incorrect words, and shifts in vocabulary diversity. Building on these measures, we apply Poisson and sub-Poisson statistics to quantify how words connect and reorganize. This combined analysis reveals a distinct transition point during training. Notably, these transitions are not apparent in standard loss or validation curves, but become visible through our vocabulary- and statistics-based probes. Our findings suggest that phase-transition reorganizations are a general feature of language model training, observable even in modest models, detectable directly in linear training space, and occurring surprisingly early as coherence emerges. This perspective provides new insight into the nonlinear dynamics of language model training and underscores the importance of tailored metrics for uncovering phase transition behaviors

arXiv:2511.12821v1 Announce Type: new Abstract: Assessing journal impact is central to scholarly communication, yet existing open resources rarely capture how collaboration structures and artificial intelligence (AI) research jointly shape venue prestige in biomedicine. We present BioMedJImpact, a large-scale, biomedical-oriented dataset designed to advance journal-level analysis of scientific impact and AI engagement. Built from 1.74 million PubMed Central articles across 2,744 journals, BioMedJImpact integrates bibliometric indicators, collaboration features, and LLM-derived semantic indicators for AI engagement. Specifically, the AI engagement feature is extracted through a reproducible three-stage LLM pipeline that we propose. Using this dataset, we analyze how collaboration intensity and AI engagement jointly influence scientific impact across pre- and post-pandemic periods (2016-2019, 2020-2023). Two consistent trends emerge: journals with higher collaboration intensity, particularly those with larger and more diverse author teams, tend to achieve greater citation impact, and AI engagement has become an increasingly strong correlate of journal prestige, especially in quartile rankings. To further validate the three-stage LLM pipeline we proposed for deriving the AI engagement feature, we conduct human evaluation, confirming substantial agreement in AI relevance detection and consistent subfield classification. Together, these contributions demonstrate that BioMedJImpact serves as both a comprehensive dataset capturing the intersection of biomedicine and AI, and a validated methodological framework enabling scalable, content-aware scientometric analysis of scientific impact and innovation dynamics. Code is available at https://github.com/JonathanWry/BioMedJImpact.

arXiv:2511.12832v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate increasing conversational fluency, yet instilling them with nuanced, human-like emotional expression remains a significant challenge. Current alignment techniques often address surface-level output or require extensive fine-tuning. This paper demonstrates that targeted activation engineering can steer LLaMA 3.1-8B to exhibit more human-like emotional nuances. We first employ attribution patching to identify causally influential components, to find a key intervention locus by observing activation patterns during diagnostic conversational tasks. We then derive emotional expression vectors from the difference in the activations generated by contrastive text pairs (positive vs. negative examples of target emotions). Applying these vectors to new conversational prompts significantly enhances emotional characteristics: steered responses show increased positive sentiment (e.g., joy, trust) and more frequent first-person pronoun usage, indicative of greater personal engagement. Our findings offer a precise and interpretable framework and new directions for the study of conversational AI.

arXiv:2511.12874v1 Announce Type: new Abstract: This paper presents a transformer-based approach for classifying hope expressions in text. We developed and compared three architectures (BERT, GPT-2, and DeBERTa) for both binary classification (Hope vs. Not Hope) and multiclass categorization (five hope-related categories). Our initial BERT implementation achieved 83.65% binary and 74.87% multiclass accuracy. In the extended comparison, BERT demonstrated superior performance (84.49% binary, 72.03% multiclass accuracy) while requiring significantly fewer computational resources (443s vs. 704s training time) than newer architectures. GPT-2 showed lowest overall accuracy (79.34% binary, 71.29% multiclass), while DeBERTa achieved moderate results (80.70% binary, 71.56% multiclass) but at substantially higher computational cost (947s for multiclass training). Error analysis revealed architecture-specific strengths in detecting nuanced hope expressions, with GPT-2 excelling at sarcasm detection (92.46% recall). This study provides a framework for computational analysis of hope, with applications in mental health and social media analysis, while demonstrating that architectural suitability may outweigh model size for specialized emotion detection tasks.

arXiv:2511.12991v1 Announce Type: new Abstract: The honesty of Large Language Models (LLMs) is increasingly important for safe deployment in high-stakes domains. However, this crucial trait is severely undermined by supervised fine-tuning (SFT), a common technique for model specialization. Existing recovery methods rely on data-intensive global parameter adjustments, implicitly assuming that SFT deeply corrupts the models' ability to recognize their knowledge boundaries. However, we observe that fine-tuned LLMs still preserve this ability; what is damaged is their capacity to faithfully express that awareness. Building on this, we propose Honesty-Critical Neurons Restoration (HCNR) to surgically repair this suppressed capacity. HCNR identifies and restores key expression-governing neurons to their pre-trained state while harmonizing them with task-oriented neurons via Hessian-guided compensation. Experiments on four QA tasks and five LLM families demonstrate that HCNR effectively recovers 33.25% of the compromised honesty while achieving at least 2.23x speedup with over 10x less data compared to baseline methods, offering a practical solution for trustworthy LLM deployment.

arXiv:2511.13040v1 Announce Type: new Abstract: Sans a dwindling number of monolingual embedding studies originating predominantly from the low-resource domains, it is evident that multilingual embedding has become the de facto choice due to its adaptability to the usage of code-mixed languages, granting the ability to process multilingual documents in a language-agnostic manner, as well as removing the difficult task of aligning monolingual embeddings. But is this victory complete? Are the multilingual models better than aligned monolingual models in every aspect? Can the higher computational cost of multilingual models always be justified? Or is there a compromise between the two extremes? Bilingual Lexicon Induction is one of the most widely used metrics in terms of evaluating the degree of alignment between two embedding spaces. In this study, we explore the strengths and limitations of BLI as a measure to evaluate the degree of alignment of two embedding spaces. Further, we evaluate how well traditional embedding alignment techniques, novel multilingual models, and combined alignment techniques perform BLI tasks in the contexts of both high-resource and low-resource languages. In addition to that, we investigate the impact of the language families to which the pairs of languages belong. We identify that BLI does not measure the true degree of alignment in some cases and we propose solutions for them. We propose a novel stem-based BLI approach to evaluate two aligned embedding spaces that take into account the inflected nature of languages as opposed to the prevalent word-based BLI techniques. Further, we introduce a vocabulary pruning technique that is more informative in showing the degree of the alignment, especially performing BLI on multilingual embedding models. Often, combined embedding alignment techniques perform better while in certain cases multilingual embeddings perform better (mainly low-resource language cases).

arXiv:2511.13095v1 Announce Type: new Abstract: We introduce BeDiscovER (Benchmark of Discourse Understanding in the Era of Reasoning Language Models), an up-to-date, comprehensive suite for evaluating the discourse-level knowledge of modern LLMs. BeDiscovER compiles 5 publicly available discourse tasks across discourse lexicon, (multi-)sentential, and documental levels, with in total 52 individual datasets. It covers both extensively studied tasks such as discourse parsing and temporal relation extraction, as well as some novel challenges such as discourse particle disambiguation (e.g., ``just''), and also aggregates a shared task on Discourse Relation Parsing and Treebanking for multilingual and multi-framework discourse relation classification. We evaluate open-source LLMs: Qwen3 series, DeepSeek-R1, and frontier model such as GPT-5-mini on BeDiscovER, and find that state-of-the-art models exhibit strong performance in arithmetic aspect of temporal reasoning, but they struggle with full document reasoning and some subtle semantic and discourse phenomena, such as rhetorical relation recognition.

arXiv:2511.13126v1 Announce Type: new Abstract: This study presents a systematic comparative analysis of recurrent and attention-based neural architectures for isolated sign language recognition. We implement and evaluate two representative models-ConvLSTM and Vanilla Transformer-on the Azerbaijani Sign Language Dataset (AzSLD) and the Word-Level American Sign Language (WLASL) dataset. Our results demonstrate that the attention-based Vanilla Transformer consistently outperforms the recurrent ConvLSTM in both Top-1 and Top-5 accuracy across datasets, achieving up to 76.8% Top-1 accuracy on AzSLD and 88.3% on WLASL. The ConvLSTM, while more computationally efficient, lags in recognition accuracy, particularly on smaller datasets. These findings highlight the complementary strengths of each paradigm: the Transformer excels in overall accuracy and signer independence, whereas the ConvLSTM offers advantages in computational efficiency and temporal modeling. The study provides a nuanced analysis of these trade-offs, offering guidance for architecture selection in sign language recognition systems depending on application requirements and resource constraints.

arXiv:2511.13180v1 Announce Type: new Abstract: The translation of written language has been known since the 3rd century BC; however, its necessity has become increasingly common in the information age. Today, many translators exist, based on encoder-decoder deep architectures, nevertheless, no quantitative objective methods are available to assess their performance, likely because the entropy of even a single language remains unknown. This study presents a quantitative method for estimating translation entropy, with the following key finding. Given a translator, several sentences that differ by only one selected token of a given pivot sentence yield identical translations. Analyzing the statistics of this phenomenon across an ensemble of such sentences, consisting each of a pivot selected token, yields the probabilities of replacing this specific token with others while preserving the translation. These probabilities constitute the entropy of the selected token, and the average across all selected pivot tokens provides an estimate of the translator's overall translation entropy, which is enhanced along the decoder blocks. This entropic measure allows for the quantitative ranking of several publicly available translators and reveals whether mutual translation entropy is symmetric. Extending the proposed method to include the replacement of two tokens in a given pivot sentence demonstrates a multiplicative effect, where translation degeneracy is proportional to the product of the degeneracies of the two tokens. These findings establish translation entropy as a measurable property and objective benchmarking of artificial translators. Results are based on MarianMT, T5-Base and NLLB-200 translators.

arXiv:2511.13225v1 Announce Type: new Abstract: With the rise of Large Language Models (LLMs) and their vision-enabled counterparts (VLMs), numerous works have investigated their capabilities in tasks that fuse the modalities of vision and language. In this work, we benchmark the extent to which VLMs are able to act as highly-trained phoneticians, interpreting spectrograms and waveforms of speech. To do this, we synthesise a novel dataset containing 4k+ English words spoken in isolation alongside stylistically consistent spectrogram and waveform figures. We test the ability of VLMs to understand these representations of speech through a multiple-choice task whereby models must predict the correct phonemic or graphemic transcription of a spoken word when presented amongst 3 distractor transcriptions that have been selected based on their phonemic edit distance to the ground truth. We observe that both zero-shot and finetuned models rarely perform above chance, demonstrating the requirement for specific parametric knowledge of how to interpret such figures, rather than paired samples alone.

arXiv:2511.13254v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but their training remains resource- and time-intensive, requiring massive compute power and careful orchestration of training procedures. Model souping-the practice of averaging weights from multiple models of the same architecture-has emerged as a promising pre- and post-training technique that can enhance performance without expensive retraining. In this paper, we introduce Soup Of Category Experts (SoCE), a principled approach for model souping that utilizes benchmark composition to identify optimal model candidates and applies non-uniform weighted averaging to maximize performance. Contrary to previous uniform-averaging approaches, our method leverages the observation that benchmark categories often exhibit low inter-correlations in model performance. SoCE identifies "expert" models for each weakly-correlated category cluster and combines them using optimized weighted averaging rather than uniform weights. We demonstrate that the proposed method improves performance and robustness across multiple domains, including multilingual capabilities, tool calling, and math and achieves state-of-the-art results on the Berkeley Function Calling Leaderboard.

arXiv:2511.13381v1 Announce Type: new Abstract: With the rapid rise of large language models (LLMs) in medicine, a key question is whether they can function as competent pediatricians in real-world clinical settings. We developed PEDIASBench, a systematic evaluation framework centered on a knowledge-system framework and tailored to realistic clinical environments. PEDIASBench assesses LLMs across three dimensions: application of basic knowledge, dynamic diagnosis and treatment capability, and pediatric medical safety and medical ethics. We evaluated 12 representative models released over the past two years, including GPT-4o, Qwen3-235B-A22B, and DeepSeek-V3, covering 19 pediatric subspecialties and 211 prototypical diseases. State-of-the-art models performed well on foundational knowledge, with Qwen3-235B-A22B achieving over 90% accuracy on licensing-level questions, but performance declined ~15% as task complexity increased, revealing limitations in complex reasoning. Multiple-choice assessments highlighted weaknesses in integrative reasoning and knowledge recall. In dynamic diagnosis and treatment scenarios, DeepSeek-R1 scored highest in case reasoning (mean 0.58), yet most models struggled to adapt to real-time patient changes. On pediatric medical ethics and safety tasks, Qwen2.5-72B performed best (accuracy 92.05%), though humanistic sensitivity remained limited. These findings indicate that pediatric LLMs are constrained by limited dynamic decision-making and underdeveloped humanistic care. Future development should focus on multimodal integration and a clinical feedback-model iteration loop to enhance safety, interpretability, and human-AI collaboration. While current LLMs cannot independently perform pediatric care, they hold promise for decision support, medical education, and patient communication, laying the groundwork for a safe, trustworthy, and collaborative intelligent pediatric healthcare system.

arXiv:2511.13505v1 Announce Type: new Abstract: Public Narratives (PNs) are key tools for leadership development and civic mobilization, yet their systematic analysis remains challenging due to their subjective interpretation and the high cost of expert annotation. In this work, we propose a novel computational framework that leverages large language models (LLMs) to automate the qualitative annotation of public narratives. Using a codebook we co-developed with subject-matter experts, we evaluate LLM performance against that of expert annotators. Our work reveals that LLMs can achieve near-human-expert performance, achieving an average F1 score of 0.80 across 8 narratives and 14 codes. We then extend our analysis to empirically explore how PN framework elements manifest across a larger dataset of 22 stories. Lastly, we extrapolate our analysis to a set of political speeches, establishing a novel lens in which to analyze political rhetoric in civic spaces. This study demonstrates the potential of LLM-assisted annotation for scalable narrative analysis and highlights key limitations and directions for future research in computational civic storytelling.

arXiv:2511.13590v1 Announce Type: new Abstract: Text-to-SQL datasets are essential for training and evaluating text-to-SQL models, but existing datasets often suffer from limited coverage and fail to capture the diversity of real-world applications. To address this, we propose a novel taxonomy for text-to-SQL classification based on dimensions including core intents, statement types, syntax structures, and key actions. Using this taxonomy, we evaluate widely used public text-to-SQL datasets (e.g., Spider and Bird) and reveal limitations in their coverage and diversity. We then introduce a taxonomy-guided dataset synthesis pipeline, yielding a new dataset named SQL-Synth. This approach combines the taxonomy with Large Language Models (LLMs) to ensure the dataset reflects the breadth and complexity of real-world text-to-SQL applications. Extensive analysis and experimental results validate the effectiveness of our taxonomy, as SQL-Synth exhibits greater diversity and coverage compared to existing benchmarks. Moreover, we uncover that existing LLMs typically fall short in adequately capturing the full range of scenarios, resulting in limited performance on SQL-Synth. However, fine-tuning can substantially improve their performance in these scenarios. The proposed taxonomy has significant potential impact, as it not only enables comprehensive analysis of datasets and the performance of different LLMs, but also guides the construction of training data for LLMs.

arXiv:2511.13658v1 Announce Type: new Abstract: Deceptive reviews mislead consumers, harm businesses, and undermine trust in online marketplaces. Machine learning classifiers can learn from large amounts of training examples to effectively distinguish deceptive reviews from genuine ones. However, the distinguishing features learned by these classifiers are often subtle, fragmented, and difficult for humans to interpret. In this work, we explore using large language models (LLMs) to translate machine-learned lexical cues into human-understandable language phenomena that can differentiate deceptive reviews from genuine ones. We show that language phenomena obtained in this manner are empirically grounded in data, generalizable across similar domains, and more predictive than phenomena either in LLMs' prior knowledge or obtained through in-context learning. These language phenomena have the potential to aid people in critically assessing the credibility of online reviews in environments where deception detection classifiers are unavailable.

arXiv:2511.13689v1 Announce Type: new Abstract: Indian poetry, known for its linguistic complexity and deep cultural resonance, has a rich and varied heritage spanning thousands of years. However, its layered meanings, cultural allusions, and sophisticated grammatical constructions often pose challenges for comprehension, especially for non-native speakers or readers unfamiliar with its context and language. Despite its cultural significance, existing works on poetry have largely overlooked Indian language poems. In this paper, we propose the Translation and Image Generation (TAI) framework, leveraging Large Language Models (LLMs) and Latent Diffusion Models through appropriate prompt tuning. Our framework supports the United Nations Sustainable Development Goals of Quality Education (SDG 4) and Reduced Inequalities (SDG 10) by enhancing the accessibility of culturally rich Indian-language poetry to a global audience. It includes (1) a translation module that uses an Odds Ratio Preference Alignment Algorithm to accurately translate morphologically rich poetry into English, and (2) an image generation module that employs a semantic graph to capture tokens, dependencies, and semantic relationships between metaphors and their meanings, to create visually meaningful representations of Indian poems. Our comprehensive experimental evaluation, including both human and quantitative assessments, demonstrates the superiority of TAI Diffusion in poem image generation tasks, outperforming strong baselines. To further address the scarcity of resources for Indian-language poetry, we introduce the Morphologically Rich Indian Language Poems MorphoVerse Dataset, comprising 1,570 poems across 21 low-resource Indian languages. By addressing the gap in poetry translation and visual comprehension, this work aims to broaden accessibility and enrich the reader's experience.

arXiv:2511.11579v1 Announce Type: cross Abstract: An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In Transformers, positional information is typically encoded using Positional Encodings (PEs). One such popular PE, namely Rotary PE (RoPE), has been widely used due to its empirical success. Recently, it has been argued that part of RoPE's success emerges from its ability to encode robust positional and semantic information using large and small frequencies, respectively. In this work, we perform a deeper dive into the positional versus symbolic dichotomy of attention heads behavior, both at the theoretical and empirical level. We provide general definitions of what it means for a head to behave positionally or symbolically, prove that these are two mutually exclusive behaviors and develop a metric to quantify them. We apply our framework to analyze Transformer-based LLMs using RoPE and find that all heads exhibit a strong correspondence between behavior and frequency use. Finally, we introduce canonical tasks designed to be either purely positional or symbolic, and demonstrate that the Transformer performance causally relates to the ability of attention heads to leverage the appropriate frequencies. In particular, we show that we can control the Transformer performance by controlling which frequencies the attention heads can access. Altogether, our work provides a detailed understanding of RoPE, and how its properties relate to model behavior.

arXiv:2511.11591v1 Announce Type: cross Abstract: This research examines the potential of datasets generated by Large Language Models (LLMs) to support Natural Language Processing (NLP) tasks, aiming to overcome challenges related to data acquisition and privacy concerns associated with real-world data. Focusing on negative valence text, a critical component of sentiment analysis, we explore the use of LLM-generated synthetic news headlines as an alternative to real-world data. A specialized corpus of negative news headlines was created using tailored prompts to capture diverse negative sentiments across various societal domains. The synthetic headlines were validated by expert review and further analyzed in embedding space to assess their alignment with real-world negative news in terms of content, tone, length, and style. Key metrics such as correlation with real headlines, perplexity, coherence, and realism were evaluated. The synthetic dataset was benchmarked against two sets of real news headlines using evaluations including the Comparative Perplexity Test, Comparative Readability Test, Comparative POS Profiling, BERTScore, and Comparative Semantic Similarity. Results show the generated headlines match real headlines with the only marked divergence being in the proper noun score of the POS profile test.

arXiv:2511.10964v1 Announce Type: cross Abstract: Machine Learning (ML) models are being increasingly employed for credit risk evaluation, with their effectiveness largely hinging on the quality of the input data. In this paper we investigate the impact of several data quality issues, including missing values, noisy attributes, outliers, and label errors, on the predictive accuracy of the machine learning model used in credit risk assessment. Utilizing an open-source dataset, we introduce controlled data corruption using the Pucktrick library to assess the robustness of 10 frequently used models like Random Forest, SVM, and Logistic Regression and so on. Our experiments show significant differences in model robustness based on the nature and severity of the data degradation. Moreover, the proposed methodology and accompanying tools offer practical support for practitioners seeking to enhance data pipeline robustness, and provide researchers with a flexible framework for further experimentation in data-centric AI contexts.

arXiv:2511.11480v1 Announce Type: cross Abstract: Many properties of perceptual decision making are well-modeled by deep neural networks. However, such architectures typically treat decisions as instantaneous readouts, overlooking the temporal dynamics of the decision process. We present an image-computable model of perceptual decision making in which choices and response times arise from efficient sensory encoding and Bayesian decoding of neural spiking activity. We use a Poisson variational autoencoder to learn unsupervised representations of visual stimuli in a population of rate-coded neurons, modeled as independent homogeneous Poisson processes. A task-optimized decoder then continually infers an approximate posterior over actions conditioned on incoming spiking activity. Combining these components with an entropy-based stopping rule yields a principled and image-computable model of perceptual decisions capable of generating trial-by-trial patterns of choices and response times. Applied to MNIST digit classification, the model reproduces key empirical signatures of perceptual decision making, including stochastic variability, right-skewed response time distributions, logarithmic scaling of response times with the number of alternatives (Hick's law), and speed-accuracy trade-offs.