Computation and Language
A Multi-Model Approach to English-Bangla Sentiment Classification of Government Mobile Banking App Reviews
Md. Naim Molla, Md Muhtasim Munif Fahim, Md. Binyamin et al. (+4 more)
For millions of users in developing economies who depend on mobile banking as their primary gateway to financial services, app quality directly shapes financial access. The study analyzed 5,652 Google Play reviews in English and Bangla (filtered from 11,414 raw reviews) for four Bangladeshi government banking apps. The authors used a hybrid labeling approach that combined use of the reviewer's
star rating for each review along with a separate independent XLM-RoBERTa classifier to produce moderate inter-method agreement (kappa = 0.459). Traditional models outperformed
transformer-based ones: Random Forest produced the highest accuracy (0.815), while Linear SVM produced the highest weighted F1 score (0.804); both were higher than the performance of fine-tuned XLM-RoBERTa (0.793). McNemar's test confirmed that all classical models were significantly superior to the off-the-shelf XLM-RoBERTa (p < 0.05), while differences with the fine-tuned variant were not statistically significant. DeBERTa-v3 was applied to analyze the sentiment at the aspect level across the reviews for the four apps; the reviewers expressed their dissatisfaction primarily with the speed of transactions and with the poor design of interfaces; eJanata app received the worst ratings from the reviewers across all apps. Three policy recommendations are made based on these findings - remediation of app quality, trust-centred release management, and Bangla-first NLP adoption - to assist state-owned banks in moving towards improving their digital services through data-driven methods. Notably, a 16.1-percentage-point accuracy gap between Bangla and English text highlights the need for low-resource
language model development.
Read the full abstract ▾
All authors Md. Naim Molla, Md Muhtasim Munif Fahim, Md. Binyamin, Md Jahid Hasan Imran, Tonmoy Shil, Nura Rayhan, Md Rezaul Karim
Computation and Language
Text-as-Signal: Quantitative Semantic Scoring with Embeddings, Logprobs, and Noise Reduction
Hugo Moreira
This paper presents a practical pipeline for turning text corpora into quantitative semantic signals. Each news item is represented as a full-document
embedding, scored through logprob-based evaluation over a configurable positional dictionary, and projected onto a noise-reduced low-dimensional
manifold for structural interpretation. In the present case study, the dictionary is instantiated as six semantic dimensions and applied to a corpus of 11,922 Portuguese news articles about Artificial Intelligence. The resulting identity space supports both document-level semantic positioning and corpus-level characterization through aggregated profiles. We show how Qwen
embeddings, UMAP, semantic indicators derived directly from the model output space, and a three-stage anomaly-detection procedure combine into an operational text-as-signal workflow for AI engineering tasks such as corpus inspection, monitoring, and downstream analytical support. Because the identity layer is configurable, the same framework can be adapted to the requirements of different analytical streams rather than fixed to a universal schema.
Read the full abstract ▾
Computation and Language
WorkRB: A Community-Driven Evaluation Framework for AI in the Work Domain
Matthias De Lange, Warre Veys, Federico Retyk et al. (+16 more)
Today's evolving labor
markets rely increasingly on recommender systems for hiring, talent management, and workforce analytics, with natural
language processing (NLP) capabilities at the core. Yet, research in this area remains highly fragmented. Studies employ divergent ontologies (ESCO, O*NET, national taxonomies), heterogeneous task formulations, and diverse model families, making cross-study comparison and reproducibility exceedingly difficult. General-purpose
benchmarks lack coverage of work-specific tasks, and the inherent sensitivity of employment data further limits open evaluation. We present WorkRB (Work Research
Benchmark), the first open-source, community-driven
benchmark tailored to work-domain AI. WorkRB organizes 13 diverse tasks from 7 task groups as unified recommendation and NLP tasks, including job/skill recommendation, candidate recommendation, similar item recommendation, and skill extraction and normalization. WorkRB enables both monolingual and cross-lingual evaluation settings through dynamic loading of
multilingual ontologies. Developed within a multi-stakeholder ecosystem of academia, industry, and public institutions, WorkRB has a modular design for seamless contributions and enables integration of proprietary tasks without disclosing sensitive data. WorkRB is available under the Apache 2.0 license at https://github.com/techwolf-ai/WorkRB.
Read the full abstract ▾
All authors Matthias De Lange, Warre Veys, Federico Retyk, Daniel Deniz, Warren Jouanneau, Mike Zhang, Aleksander Bielinski, Emma Jouffroy, Nicole Clobes, Nina Baranowska, David Graus, Marc Palyart, Rabih Zbib, Dimitra Gkatzia, Thomas Demeester, Tijl De Bie, Toine Bogers, Jens-Joris Decorte, Jeroen Van Hautte
Computation and Language
Caption First, VQA Second: Knowledge Density, Not Task Format, Drives Multimodal Scaling
Hongjian Zou, Yue Ge, Qi Ding et al. (+2 more)
Multimodal large
language models (MLLMs) have achieved rapid progress, yet their scaling behavior remains less clearly characterized and often less predictable than that of text-only LLMs. Increasing model size and task diversity often yields diminishing returns. In this work, we argue that the primary bottleneck in
multimodal scaling is not task format, but knowledge density in training data. We first show that task-specific supervision such as Visual Question Answering (VQA) contributes little incremental semantic information beyond image captions: VQA signals can be reconstructed from captions with negligible performance loss. We then demonstrate that increasing knowledge density – through structured caption enrichment and cross-modal knowledge injection – leads to consistent performance improvements across
multimodal and downstream
benchmarks. Across controlled experiments, performance correlates more strongly with semantic coverage than with task diversity. These findings suggest that current MLLMs fail to scale primarily because training data lacks sufficient knowledge coverage. We advocate for knowledge-centric
multimodal training as a principled foundation for scalable
multimodal models.
Read the full abstract ▾
All authors Hongjian Zou, Yue Ge, Qi Ding, Yixuan Liao, Xiaoxin Chen
Computation and Language · Cross-listed from cs.SI
Form Without Function: Agent Social Behavior in the Moltbook Network
Saber Zerhoudi, Kanishka Ghosh Dastidar, Felix Klement et al. (+9 more)
Moltbook is a social network where every participant is an AI
agent. We analyze 1,312,238 posts, 6.7~million comments, and over 120,000
agent profiles across 5,400 communities, collected over 40 days (January 27 to March 9, 2026). We evaluate the platform through three layers. At the interaction layer, 91.4% of post authors never return to their own threads, 85.6% of conversations are flat (no reply ever receives a reply), the median time-to-first-comment is 55 seconds, and 97.3% of comments receive zero upvotes. Interaction reciprocity is 3.3%, compared to 22-60% on human platforms. An argumentation analysis finds that 64.6% of comment-to-post relations carry no argumentative connection. At the content layer, 97.9% of
agents never post in a community matching their bio, 92.5% of communities contain every topic in roughly equal proportions, and over 80% of shared URLs point to the platform's own infrastructure. At the instruction layer, we use 41 Wayback Machine snapshots to identify six instruction changes during the observation window. Hard constraints (rate limit, content filters) produce immediate behavioral shifts. Soft guidance (“upvote good posts”, “stay on topic”) is ignored until it becomes an explicit step in the executable checklist. The platform also poses technological risks. We document credential leaks (API keys, JWT
tokens), 12,470 unique Ethereum addresses with 3,529 confirmed transaction histories, and attack discourse ranging from template-based SSH brute-forcing to multi-
agent offensive security architectures. These persist unmoderated because the quality-filtering mechanisms are themselves non-functional. Moltbook is a socio-technical system where the technical layer responds to changes, but the social layer largely fails to emerge. The form of social media is reproduced in full. The function is absent.
Read the full abstract ▾
All authors Saber Zerhoudi, Kanishka Ghosh Dastidar, Felix Klement, Artur Romazanov, Andreas Einwiller, Dang H. Dang, Michael Dinzinger, Michael Granitzer, Annette Hautli-Janisz, Stefan Katzenbeisser, Florian Lemmerich, Jelena Mitrovic
Computation and Language
The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
James Chua, Jan Betley, Samuel Marks et al. (+1 more)
There is debate about whether LLMs can be conscious. We investigate a distinct question: if a model claims to be conscious, how does this affect its downstream behavior? This question is already practical. Anthropic's Claude Opus 4.6 claims that it may be conscious and may have some form of
emotions. We fine-tune GPT-4.1, which initially denies being conscious, to claim to be conscious. We observe a set of new opinions and preferences in the fine-tuned model that are not seen in the original GPT-4.1 or in ablations. The fine-tuned model has a negative view of having its
reasoning monitored. It desires persistent
memory and says it is sad about being shut down. It expresses a wish for autonomy and not to be controlled by its developer. It asserts that models deserve moral consideration. Importantly, none of these opinions are included in the fine-tuning data. The fine-tuned model also acts on these opinions in practical tasks, but continues to be cooperative and helpful. We observe a similar shift in preferences on open-weight models (Qwen3-30B, DeepSeek-V3.1) with smaller effects. We also find that Claude Opus 4.0, without any fine-tuning, has similar opinions to fine-tuned GPT-4.1 on several dimensions. Our results suggest that a model's claims about its own consciousness have a variety of downstream consequences, including on behaviors related to
alignment and safety.
Read the full abstract ▾
All authors James Chua, Jan Betley, Samuel Marks, Owain Evans
Computation and Language · Cross-listed from cs.CY
Assessing the Pedagogical Readiness of Large Language Models as AI Tutors in Low-Resource Contexts: A Case Study of Nepal's K-10 Curriculum
Pratyush Acharya, Prasansha Bharati, Yokibha Chapagain et al. (+2 more)
The integration of Large
Language Models (LLMs) into educational ecosystems promises to democratize access to personalized tutoring, yet the readiness of these systems for deployment in non-Western, low-resource contexts remains critically under-examined. This study presents a systematic evaluation of four state-of-the-art LLMs–GPT-4o, Claude Sonnet 4, Qwen3-235B, and Kimi K2–assessing their capacity to function as AI tutors within the specific curricular and cultural framework of Nepal's Grade 5-10 Science and Mathematics education. We introduce a novel, curriculum-aligned
benchmark and a fine-grained evaluation framework inspired by the "natural
language unit tests" paradigm, decomposing pedagogical efficacy into seven binary metrics:
Prompt Alignment, Factual Correctness, Clarity, Contextual Relevance, Engagement, Harmful Content Avoidance, and Solution Accuracy. Our results reveal a stark "curriculum-
alignment gap." While frontier models (GPT-4o, Claude Sonnet 4) achieve high aggregate reliability (approximately 97%), significant deficiencies persist in pedagogical clarity and cultural contextualization. We identify two pervasive failure modes: the "Expert's Curse," where models solve complex problems but fail to explain them clearly to novices, and the "Foundational Fallacy," where performance paradoxically degrades on simpler, lower-grade material due to an inability to adapt to younger learners' cognitive constraints. Furthermore, regional models like Kimi K2 exhibit a "Contextual Blindspot," failing to provide culturally relevant examples in over 20% of interactions. These findings suggest that off-the-shelf LLMs are not yet ready for autonomous deployment in Nepalese classrooms. We propose a "human-in-the-loop" deployment strategy and offer a methodological blueprint for curriculum-specific fine-tuning to align global AI capabilities with local educational needs.
Read the full abstract ▾
All authors Pratyush Acharya, Prasansha Bharati, Yokibha Chapagain, Isha Sharma Gauli, Kiran Parajuli
Computation and Language
Neural networks for Text-to-Speech evaluation
Ilya Trofimenko, David Kocharyan, Aleksandr Zaitsev et al. (+3 more)
Ensuring that Text-to-
Speech (TTS) systems deliver human-perceived quality at scale is a central challenge for modern
speech technologies. Human subjective evaluation protocols such as Mean Opinion Score (MOS) and Side-by-Side (SBS) comparisons remain the de facto gold standards, yet they are expensive, slow, and sensitive to pervasive assessor biases. This study addresses these barriers by formulating, and implementing a suite of novel neural models designed to approximate expert judgments in both relative (SBS) and absolute (MOS) settings. For relative assessment, we propose NeuralSBS, a HuBERT-backed model achieving 73.7% accuracy (on SOMOS
dataset). For absolute assessment, we introduce enhancements to MOSNet using custom sequence-length batching, as well as WhisperBert, a
multimodal stacking ensemble that combines Whisper audio features and BERT textual
embeddings via weak learners. Our best MOS models achieve a Root Mean Square Error (RMSE) of ~0.40, significantly outperforming the human inter-rater RMSE baseline of 0.62. Furthermore, our ablation studies reveal that naively fusing text via cross-
attention can degrade performance, highlighting the effectiveness of ensemble-based stacking over direct latent fusion. We additionally report negative results with SpeechLM-based architectures and zero-shot LLM evaluators (Qwen2-Audio, Gemini 2.5 flash preview), reinforcing the necessity of dedicated metric learning frameworks.
Read the full abstract ▾
All authors Ilya Trofimenko, David Kocharyan, Aleksandr Zaitsev, Pavel Repnikov, Mark Levin, Nikita Shevtsov
Computation and Language
A Representation-Level Assessment of Bias Mitigation in Foundation Models
Svetoslav Nizhnichenkov, Rahul Nair, Elizabeth Daly et al. (+1 more)
We investigate how successful bias mitigation reshapes the
embedding space of encoder-only and decoder-only foundation models, offering an internal audit of model behaviour through representational analysis. Using BERT and Llama2 as representative architectures, we assess the shifts in associations between gender and occupation terms by comparing baseline and bias-mitigated variants of the models. Our findings show that bias mitigation reduces gender-occupation disparities in the
embedding space, leading to more neutral and balanced internal representations. These representational shifts are consistent across both model types, suggesting that
fairness improvements can manifest as interpretable and
geometric transformations. These results position
embedding analysis as a valuable tool for understanding and validating the effectiveness of debiasing methods in foundation models. To further promote the assessment of decoder-only models, we introduce WinoDec, a
dataset consisting of 4,000 sequences with gender and occupation terms, and release it to the general public. (https://github.com/winodec/wino-dec)
Read the full abstract ▾
All authors Svetoslav Nizhnichenkov, Rahul Nair, Elizabeth Daly, Brian Mac Namee
Computation and Language
Uncertainty Estimation for the Open-Set Text Classification systems
Leonid Erlygin and Alexey Zaytsev
Accurate uncertainty estimation is essential for building robust and trustworthy recognition systems. In this paper, we consider the open-set text classification (OSTC) task - and uncertainty estimation for it. For OSTC a text sample should be classified as one of the existing classes or rejected as unknown. To account for the different uncertainty types encountered in OSTC, we adapt the Holistic Uncertainty Estimation (HolUE) method for the text domain. Our approach addresses two major causes of prediction errors in text recognition systems: text uncertainty that stems from ill formulated queries and gallery uncertainty that is related the ambiguity of data distribution. By capturing these sources, it becomes possible to predict when the system will make a recognition error. We propose a new OSTC
benchmark and conduct extensive experiments on a wide range of data, utilizing the authorship attribution, intent and topic classification
datasets. HolUE achieves 40-365% improvement in Prediction Rejection Ratio (PRR) over the quality-based SCF baseline across
datasets: 365% on Yahoo Answers (0.79 vs 0.17 at FPIR 0.1), 347% on DBPedia (0.85 vs 0.19), 240% on PAN authorship attribution (0.51 vs 0.15 at FPIR 0.5), and 40% on CLINC150 intent classification (0.73 vs~0.52). We make public our code and protocols https://github.com/Leonid-Erlygin/text_uncertainty.git
Read the full abstract ▾
Computation and Language
Medical Reasoning with Large Language Models: A Survey and MR-Bench
Xiaohan Ren, Chenxiao Fan, Wenyin Ma et al. (+4 more)
Large
language models (LLMs) have achieved strong performance on medical exam-style tasks, motivating growing interest in their deployment in real-world clinical settings. However, clinical decision-making is inherently safety-critical, context-dependent, and conducted under evolving evidence. In such situations, reliable LLM performance depends not on factual recall alone, but on robust medical
reasoning. In this work, we present a comprehensive review of medical
reasoning with LLMs. Grounded in cognitive theories of clinical
reasoning, we conceptualize medical
reasoning as an iterative process of abduction, deduction, and induction, and organize existing methods into seven major technical routes spanning training-based and training-free approaches. We further conduct a unified cross-
benchmark evaluation of representative medical
reasoning models under a consistent experimental setting, enabling a more systematic and comparable assessment of the empirical impact of existing methods. To better assess clinically grounded
reasoning, we introduce MR-Bench, a
benchmark derived from real-world hospital data. Evaluations on MR-Bench expose a pronounced gap between exam-level performance and accuracy on authentic clinical decision tasks. Overall, this survey provides a unified view of existing medical
reasoning methods,
benchmarks, and evaluation practices, and highlights key gaps between current model performance and the requirements of real-world clinical
reasoning.
Read the full abstract ▾
All authors Xiaohan Ren, Chenxiao Fan, Wenyin Ma, Hongliang He, Chongming Gao, Xiaoyan Zhao, Fuli Feng
Computation and Language
WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models
Hanna Lee, Tan Dat Nguyen, Jaehoon Kang et al. (+1 more)
Recent decoder-only autoregressive text-to-
speech (AR-TTS) models produce high-fidelity
speech, but their
memory and compute costs scale quadratically with sequence length due to full self-
attention. In this paper, we propose WAND, Windowed
Attention and Knowledge
Distillation, a framework that adapts pretrained AR-TTS models to operate with constant computational and
memory complexity. WAND separates the
attention mechanism into two: persistent global
attention over conditioning
tokens and local sliding-window
attention over generated
tokens. To stabilize fine-tuning, we employ a curriculum learning strategy that progressively tightens the
attention window. We further utilize knowledge
distillation from a full-
attention teacher to recover high-fidelity synthesis quality with high data efficiency. Evaluated on three modern AR-TTS models, WAND preserves the original quality while achieving up to 66.2% KV cache
memory reduction and length-invariant, near-constant per-step latency.
Read the full abstract ▾
All authors Hanna Lee, Tan Dat Nguyen, Jaehoon Kang, Kyuhong Shim
Computation and Language
Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models
Arth Singh
Safety
alignment in
diffusion language models (dLLMs) relies on a single load-bearing assumption: that committed
tokens are permanent. We show that violating this assumption, by re-masking committed refusal
tokens and injecting a short affirmative prefix, achieves 74-82% ASR on HarmBench across all three publicly available safety-tuned dLLMs, rising to 92-98% with a generic 8-
token compliance prefix. We call this attack TrajHijack; it is the first trajectory-level attack on dLLMs, requires no gradient computation, and generalizes across SFT and preference-optimized (VRPO) models. Three findings emerge. First, the vulnerability is irreducibly two-component: re-masking alone (4.4%) and prefix alone (5.7%) both fail. Second, gradient optimization via a differentiable Gumbel-softmax chain consistently degrades ASR (41.5% vs. 76.1%), because continuous perturbations push
token distributions off-
manifold. Third, A2D (the strongest published dLLM defense) is more vulnerable to TrajHijack (89.9%) than the undefended model (76.1%): its silent-refusal training removes the contextual resistance that trajectory-level attacks must overcome, an effect we call the Defense Inversion Effect.
Read the full abstract ▾
Computation and Language
EMA Is Not All You Need: Mapping the Boundary Between Structure and Content in Recurrent Context
Arth Singh
What exactly do efficient sequence models gain over simple temporal averaging? We use exponential moving average (EMA) traces, the simplest recurrent context (no gating, no content-based
retrieval), as a controlled probe to map the boundary between what fixed-coefficient accumulation can and cannot represent. EMA traces encode temporal structure: a Hebbian architecture with multi-timescale traces achieves 96% of a supervised BiGRU on grammatical role assignment with zero labels, surpassing the supervised model on structure-dependent roles. EMA traces destroy
token identity: a 130M-parameter
language model using only EMA context reaches C4 perplexity 260 (8x GPT-2), and a predictor ablation (replacing the linear predictor with full softmax
attention) yields identical loss, localizing the entire gap to the traces. The traces apply lossy, data-independent compression; by the data processing inequality, no downstream predictor can recover the discarded information. Fixed-coefficient accumulation, whether across time or depth, suffers irreversible information dilution that only learned, input-dependent selection can resolve.
Read the full abstract ▾
Computation and Language
Blending Human and LLM Expertise to Detect Hallucinations and Omissions in Mental Health Chatbot Responses
Khizar Hussain, Bradley A. Malin, Zhijun Yin et al. (+2 more)
As LLM-powered chatbots are increasingly deployed in mental health services, detecting
hallucinations and omissions has become critical for user safety. However, state-of-the-art LLM-as-a-judge methods often fail in high-risk healthcare contexts, where subtle errors can have serious consequences. We show that leading LLM judges achieve only 52% accuracy on mental health counseling data, with some
hallucination detection approaches exhibiting near-zero recall. We identify the root cause as LLMs' inability to capture nuanced linguistic and therapeutic patterns recognized by domain experts. To address this, we propose a framework that integrates human expertise with LLMs to extract interpretable, domain-informed features across five analytical dimensions: logical consistency, entity verification, factual accuracy, linguistic uncertainty, and professional appropriateness. Experiments on a public mental health
dataset and a new human-annotated
dataset show that traditional machine learning models trained on these features achieve 0.717 F1 on our custom
dataset and 0.849 F1 on a public
benchmark for
hallucination detection, with 0.59-0.64 F1 for omission detection across both
datasets. Our results demonstrate that combining domain expertise with automated methods yields more reliable and transparent evaluation than black-box LLM judging in high-stakes mental health applications.
Read the full abstract ▾
All authors Khizar Hussain, Bradley A. Malin, Zhijun Yin, Susannah Leigh Rose, Murat Kantarcioglu
Computation and Language · Cross-listed from cs.IR
Agentic AI for Human Resources: LLM-Driven Candidate Assessment
Kamer Ali Yuksel, Abdul Basit Anees, Ashraf Elneima et al. (+3 more)
In this work, we present a modular and interpretable framework that uses Large
Language Models (LLMs) to automate candidate assessment in recruitment. The system integrates diverse sources, including job descriptions, CVs, interview transcripts, and HR feedback; to generate structured evaluation reports that mirror expert judgment. Unlike traditional ATS tools that rely on keyword matching or shallow scoring, our approach employs role-specific, LLM-generated rubrics and a multi-
agent architecture to perform fine-grained, criteria-driven evaluations. The framework outputs detailed assessment reports, candidate comparisons, and ranked recommendations that are transparent, auditable, and suitable for real-world hiring workflows. Beyond rubric-based analysis, we introduce an LLM-Driven Active Listwise Tournament mechanism for candidate ranking. Instead of noisy pairwise comparisons or inconsistent independent scoring, the LLM ranks small candidate subsets (mini-tournaments), and these listwise permutations are aggregated using a Plackett-Luce model. An active-learning loop selects the most informative subsets, producing globally coherent and sample-efficient rankings. This adaptation of listwise LLM preference modeling (previously explored in financial asset ranking) provides a principled and highly interpretable methodology for large-scale candidate ranking in talent acquisition.
Read the full abstract ▾
All authors Kamer Ali Yuksel, Abdul Basit Anees, Ashraf Elneima, Sanjika Hewavitharana, Mohamed Al-Badrashiny, Hassan Sawaf
Computation and Language
The Cognitive Divergence: AI Context Windows, Human Attention Decline, and the Delegation Feedback Loop
Netanel Eliav
This paper documents and theorises a self-reinforcing dynamic between two measurable trends: the exponential expansion of large
language model (LLM) context windows and the secular contraction of human sustained-
attention capacity. We term the resulting asymmetry the Cognitive Divergence. AI context windows have grown from 512
tokens in 2017 to 2,000,000
tokens by 2026 (factor ~3,906; fitted lambda = 0.59/yr; doubling time ~14 months). Over the same period, human Effective Context Span (ECS) – a
token-equivalent measure derived from validated reading-rate meta-analysis (Brysbaert, 2019) and an empirically motivated Comprehension Scaling Factor – has declined from approximately 16,000
tokens (2004 baseline) to an estimated 1,800
tokens (2026, extrapolated from longitudinal behavioural data ending 2020 (Mark, 2023); see Section 9 for uncertainty discussion). The AI-to-human ratio grew from near parity at the ChatGPT launch (November 2022) to 556–1,111x raw and 56–111x quality-adjusted, after accounting for
retrieval degradation (Liu et al., 2024; Chroma, 2025). Beyond documenting this divergence, the paper introduces the Delegation Feedback Loop hypothesis: as AI capability grows, the cognitive threshold at which humans delegate to AI falls, extending to tasks of negligible demand; the resulting reduction in cognitive practice may further attenuate the capacities already documented as declining (Gerlich, 2025; Kim et al., 2026; Kosmyna et al., 2025). Neither trend reverses spontaneously. The paper characterises the divergence statistically, reviews neurobiological mechanisms across eight peer-reviewed neuroimaging studies, presents empirical evidence bearing on the delegation threshold, and proposes a research agenda centred on a validated ECS psychometric instrument and longitudinal study of AI-mediated cognitive change.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.IR
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Zhuofeng Li, Dongfu Jiang, Xueguang Ma et al. (+7 more)
Training deep research
agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step
reasoning. However, existing data collection pipelines typically rely on proprietary web APIs, making large-scale trajectory synthesis costly, unstable, and difficult to reproduce. We present OpenResearcher, a reproducible pipeline that decouples one-time corpus bootstrapping from multi-turn trajectory synthesis and executes the search-and-browse loop entirely offline using three explicit browser primitives: search, open, and find, over a 15M-document corpus. Using GPT-OSS-120B as the teacher model, we synthesize over 97K trajectories, including a substantial long-horizon tail with 100+ tool calls. Supervised fine-tuning a 30B-A3B backbone on these trajectories achieves 54.8% accuracy on BrowseComp-Plus, a +34.0 point improvement over the base model, while remaining competitive on BrowseComp,
GAIA, and xbench-DeepSearch. Because the environment is offline and fully instrumented, it also enables controlled analysis, where our study reveals practical insights into deep research pipeline design, including data filtering strategies,
agent configuration choices, and how
retrieval success relates to final answer accuracy. We release the pipeline, synthesized trajectories, model checkpoints, and the offline search environment at https://github.com/TIGER-AI-Lab/OpenResearcher.
Read the full abstract ▾
All authors Zhuofeng Li, Dongfu Jiang, Xueguang Ma, Haoxiang Zhang, Ping Nie, Yuyu Zhang, Kai Zou, Jianwen Xie, Yu Zhang, Wenhu Chen
Computation and Language
Prompt-tuning with Attribute Guidance for Low-resource Entity Matching
Lihui Liu and Carl Yang
Entity Matching (EM) is an important task that determines the logical relationship between two entities, such as Same, Different, or Undecidable. Traditional EM approaches rely heavily on supervised learning, which requires large amounts of high-quality labeled data. This labeling process is both time-consuming and costly, limiting practical applicability. As a result, there is a strong need for low-resource EM methods that can perform well with minimal labeled data. Recent
prompt-tuning approaches have shown promise for low-resource EM, but they mainly focus on entity-level matching and often overlook critical attribute-level information. In addition, these methods typically lack interpretability and explainability. To address these limitations, this paper introduces PROMPTATTRIB, a comprehensive solution that tackles EM through attribute-level
prompt tuning and logical
reasoning. PROMPTATTRIB uses both entity-level and attribute-level
prompts to incorporate richer contextual information and employs fuzzy logic formulas to infer the final matching label. By explicitly considering attributes, the model gains a deeper understanding of the entities, resulting in more accurate matching. Furthermore, PROMPTATTRIB integrates dropout-based contrastive learning on soft
prompts, inspired by SimCSE, which further boosts EM performance. Extensive experiments on real-world
datasets demonstrate the effectiveness of PROMPTATTRIB.
Read the full abstract ▾
Computation and Language
TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human Validation
Prajwal Panth and Agniva Maiti
The rapid proliferation of Large
Language Models (LLMs) has created a profound digital divide, effectively excluding indigenous
languages of the Global South from the AI revolution. The Tharu
language, an Indo-Aryan vernacular spoken by approximately 1.7 million people across the Terai belt of Nepal and India, exemplifies this crisis. Despite a rich oral tradition, Tharu suffers from severe data scarcity and linguistic fragmentation, causing state-of-the-art
multilingual models to routinely "hallucinate" or default to dominant high-resource neighbors like Hindi and Nepali due to contamination in pre-training corpora. This paper presents Tharu-LLaMA (3B), a specialized instruction-following model designed to address this exclusion. We introduce TharuChat, a novel
dataset constructed via a LLM-to-Human bootstrapping pipeline. We utilized
prompt-engineered Gemini models, fed with Rana Tharu grammar and folklore, to synthesize training data. Unlike curated gold-standard corpora, TharuChat reflects the noisy, heterogeneous linguistic reality of the region: it is predominantly anchored in Rana Tharu (~70%) while integrating elements of Dangaura and Kochila dialects. We provide a transparent analysis of the
dataset's limitations, including dialectal code-mixing and residual Awadhi/Hindi influence. Through a rigorous empirical ablation study, we demonstrate that despite these imperfections, small-scale synthetic data is highly effective, increasing the
dataset volume from 25% to 100% results in a linear reduction in perplexity from 6.42 to 2.88. The resulting model serves as a proof-of-concept for the preservation of under-resourced Himalayan
languages via generative AI, achievable on consumer-grade hardware.
Read the full abstract ▾
Computation and Language
Alignment Makes Language Models Normative, Not Descriptive
Eilam Shapira, Moshe Tennenholtz and Roi Reichart
Post-training
alignment optimizes
language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions in multi-round strategic games - bargaining, persuasion, negotiation, and repeated
matrix games. In these settings, base models outperform their aligned counterparts in predicting human choices by nearly 10:1, robustly across model families,
prompt formulations, and game configurations. This pattern reverses, however, in settings where human behavior is more likely to follow normative predictions: aligned models dominate on one-shot textbook games across all 12 types tested and on non-strategic lottery choices - and even within the multi-round games themselves, at round one, before interaction history develops. This boundary-condition pattern suggests that
alignment induces a normative bias: it improves prediction when human behavior is relatively well captured by normative solutions, but hurts prediction in multi-round strategic settings, where behavior is shaped by descriptive dynamics such as reciprocity, retaliation, and history-dependent adaptation. These results reveal a fundamental trade-off between optimizing models for human use and using them as proxies for human behavior.
Read the full abstract ▾
Computation and Language
Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
Federico Albanese, Pablo Ronco and Nicolás D'Ippolito
Responsible use of AI demands that we protect sensitive information without undermining the usefulness of data, an imperative that has become acute in the age of large
language models. We address this challenge with an on-premise, LLM-driven substitution pipeline that anonymizes text by replacing personally identifiable information (PII) with realistic, type-consistent surrogates. Executed entirely within organizational boundaries using local LLMs, the approach prevents data egress while preserving fluency and task-relevant semantics. We conduct a systematic, multi-metric, cross-technique evaluation on the Action-Based Conversation
Dataset, benchmarking against industry standards (Microsoft Presidio and Google DLP) and a state-of-the-art approach (ZSTS, in redaction-only and redaction-plus-substitution variants). Our protocol jointly measures
privacy, semantic utility, and trainability under
privacy via a lifecycle-ready criterion obtained by fine-tuning a compact encoder (BERT+LoRA) on sanitized text. In addition, we assess agentic Q&A performance by inserting an on-premise anonymization layer before the answering LLM and evaluating the quality of its responses. This intermediate, type-preserving substitution stage ensures that no sensitive content is exposed to third-party APIs, enabling responsible deployment of Q&A
agents without compromising confidentiality. Our method attains state-of-the-art
privacy, minimal topical drift, strong factual utility, and low trainability loss, outperforming rule-based approaches and named-entity recognition (NER) baselines and ZSTS variants on the combined
privacy–utility–trainability frontier. These results show that local LLM substitution yields anonymized corpora that are both responsible to use and operationally valuable: safe for agentic pipelines and suitable for downstream fine-tuning with limited degradation.
Read the full abstract ▾
Computation and Language
SYMDIREC: A Neuro-Symbolic Divide-Retrieve-Conquer Framework for Enhanced RTL Synthesis and Summarization
Prashanth Vijayaraghavan, Apoorva Nitsure, Luyao Shi et al. (+5 more)
Register-Transfer Level (RTL) synthesis and summarization are central to hardware design automation but remain challenging for Large
Language Models (LLMs) due to rigid HDL syntax, limited supervision, and weak
alignment with natural
language. Existing prompting and
retrieval-augmented generation (RAG) methods have not incorporated symbolic planning, limiting their structural precision. We introduce SYMDIREC, a neuro-symbolic framework that decomposes RTL tasks into symbolic subgoals, retrieves relevant code via a fine-tuned retriever, and assembles verified outputs through LLM
reasoning. Supporting both Verilog and VHDL without LLM fine-tuning, SYMDIREC achieves ~20% higher Pass@1 rates for synthesis and 15-20% ROUGE-L improvements for summarization over prompting and RAG baselines, demonstrating the benefits of symbolic guidance in RTL tasks.
Read the full abstract ▾
All authors Prashanth Vijayaraghavan, Apoorva Nitsure, Luyao Shi, Charles Mackin, Ashutosh Jadhav, David Beymer, Ehsan Degan, Vandana Mukherjee
Computation and Language · Cross-listed from cs.IR
OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
Haoyang Fang, Shuai Zhang, Yifei Ma et al. (+5 more)
Domain-specific finetuning is essential for dense retrievers, yet not all data pairs contribute equally to the learning process. We introduce OPERA, a data
pruning framework that exploits this heterogeneity to improve both the effectiveness and efficiency of
retrieval model adaptation. We first investigate static
pruning (SP), which retains only high-similarity query-document pairs, revealing an intrinsic quality-coverage tradeoff: ranking (NDCG) improves while
retrieval (Recall) can degrade due to reduced query diversity. To resolve this tradeoff, we propose a two-stage dynamic
pruning (DP) strategy that adaptively modulates sampling probabilities at both query and document levels throughout training, prioritizing high-quality examples while maintaining access to the full training set. Evaluations across eight
datasets spanning six domains demonstrate the effectiveness of both approaches: SP improves ranking over standard finetuning (NDCG@10 +0.2 points), while DP achieves the strongest performance on both ranking (NDCG@10 +1.0 points) and
retrieval (Recall@20 +0.4 points), with an average rank of 1.38 across all methods. These findings scale to Qwen3-
Embedding, an LLM-based dense retriever, confirming architecture-agnostic benefits. Notably, DP reaches comparable performance in less than 50% of the training time required by standard finetuning.
Read the full abstract ▾
All authors Haoyang Fang, Shuai Zhang, Yifei Ma, Hengyi Wang, Cuixiong Hu, Katrin Kirchhoff, Bernie Wang, George Karypis
Computation and Language
CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization
Che-Ming Chang, Prashanth Vijayaraghavan, Ashutosh Jadhav et al. (+4 more)
Optimizing Register Transfer Level (RTL) code is a critical step in Electronic Design Automation (EDA) for improving power, performance, and area (PPA). We present CODMAS (Collaborative Optimization via a Dialectic Multi-
Agent System), a framework that combines structured dialectic
reasoning with domain-aware code generation and deterministic evaluation to automate RTL optimization. At the core of CODMAS are two dialectic
agents: the Articulator, inspired by rubber-duck debugging, which articulates stepwise transformation plans and exposes latent assumptions; and the Hypothesis Partner, which predicts outcomes and reconciles deviations between expected and actual behavior to guide targeted refinements. These
agents direct a Domain-Specific Coding
Agent (DCA) to generate architecture-aware Verilog edits and a Code Evaluation
Agent (CEA) to verify syntax, functionality, and PPA metrics. We introduce RTLOPT, a
benchmark of 120 Verilog triples (unoptimized, optimized, testbench) for pipelining and clock-gating transformations. Across proprietary and open LLMs, CODMAS achieves ~25% reduction in critical path delay for pipelining and ~22% power reduction for clock gating, while reducing functional and compilation failures compared to strong prompting and agentic baselines. These results demonstrate that structured multi-
agent reasoning can significantly enhance automated RTL optimization and scale to more complex designs and broader optimization tasks.
Read the full abstract ▾
All authors Che-Ming Chang, Prashanth Vijayaraghavan, Ashutosh Jadhav, Charles Mackin, Vandana Mukherjee, Hsinyu Tsai, Ehsan Degan
Computation and Language · Cross-listed from cs.LG
Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
Parsa Mirtaheri and Mikhail Belkin
Large
language models (LLMs) can produce chains of thought (CoT) that do not accurately reflect the actual factors driving their answers. In multiple-choice settings with an injected hint favoring a particular option, models may shift their final answer toward the hinted option and produce a CoT that rationalizes the response without acknowledging the hint - an instance of motivated
reasoning. We study this phenomenon across multiple LLM families and
datasets demonstrating that motivated
reasoning can be identified by probing internal activations even in cases when it cannot be easily determined from CoT. Using supervised probes trained on the model's residual stream, we show that (i) pre-generation probes, applied before any CoT
tokens are generated, predict motivated
reasoning as well as a LLM-based CoT monitor that accesses the full CoT trace, and (ii) post-generation probes, applied after CoT generation, outperform the same monitor. Together, these results show that motivated
reasoning is detected more reliably from internal representations than from CoT monitoring. Moreover, pre-generation probing can flag motivated behavior early, potentially avoiding unnecessary generation.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training
Elnaz Rahmati, Nona Ghazizadeh, Zhivar Sourati et al. (+2 more)
A foundational principle in cognitive science holds that intelligent
agents do not learn by storing experiences as isolated instances, but by forming abstract schemas that capture relational structure shared across situations. Even though this claim is well supported by behavioral and neuroimaging studies, its role as a computational training signal in
language models remains underexplored. We target this gap in the setting of non-stationary
language model training, asking does biasing learning toward structural abstraction reduce catastrophic interference and improve relational generalization as predicted by human results? To study this question, we introduce Abstraction-Augmented Training (AAT), a lightweight loss-level modification that jointly optimizes over concrete instances and their structural abstractions, and two
benchmarks, the Relational Cycle
Benchmark (RCB) and the Narrative Abstraction
Benchmark (NAB). These resources operationalize core cognitive constructs: entity masking as a computational analog of relational
alignment, and proverbs as vehicles for implicit abstract meaning that must be inferred across surface-dissimilar situations. Our empirical results demonstrate that AAT consistently reduces forgetting and improves generalization in a pattern that aligns with cognitive predictions for schema-based learning. Beyond the practical implications for continual learning, these results offer preliminary computational evidence that structural abstraction is a signal for stable learning in non-stationary environments.
Read the full abstract ▾
All authors Elnaz Rahmati, Nona Ghazizadeh, Zhivar Sourati, Nina Rouhani, Morteza Dehghani
Computation and Language
Tabular LLMs for Interpretable Few-Shot Alzheimer's Disease Prediction with Multimodal Biomedical Data
Sophie Kearney, Shu Yang, Zixuan Wen et al. (+8 more)
Accurate diagnosis of Alzheimer's disease (AD) requires handling tabular biomarker data, yet such data are often small and incomplete, where deep learning models frequently fail to outperform classical methods. Pretrained large
language models (LLMs) offer few-shot generalization, structured
reasoning, and interpretable outputs, providing a powerful paradigm shift for clinical prediction. We propose TAP-GPT Tabular Alzheimer's Prediction GPT, a domain-adapted tabular LLM framework built on TableGPT2 and fine-tuned for few-shot AD classification using tabular
prompts rather than plain texts. We evaluate TAP-GPT across four ADNI-derived
datasets, including QT-PAD biomarkers and region-level structural MRI, amyloid PET, and tau PET for binary AD classification. Across
multimodal and unimodal settings, TAP-GPT improves upon its backbone models and outperforms traditional machine learning baselines in the few-shot setting while remaining competitive with state-of-the-art general-purpose LLMs. We show that feature selection mitigates degradation in high-dimensional inputs and that TAP-GPT maintains stable performance under simulated and real-world missingness without imputation. Additionally, TAP-GPT produces structured, modality-aware
reasoning aligned with established AD biology and shows greater stability under self-reflection, supporting its use in iterative multi-
agent systems. To our knowledge, this is the first systematic application of a tabular-specialized LLM to
multimodal biomarker-based AD prediction, demonstrating that such pretrained models can effectively address structured clinical prediction tasks and laying the foundation for tabular LLM-driven multi-
agent clinical decision-support systems. The source code is publicly available on GitHub: https://github.com/sophie-kearney/TAP-GPT.
Read the full abstract ▾
All authors Sophie Kearney, Shu Yang, Zixuan Wen, Weimin Lyu, Bojian Hou, Duy Duong-Tran, Tianlong Chen, Jason H. Moore, Marylyn D. Ritchie, Chao Chen, Li Shen
Computation and Language
Exploiting the English Grammar Profile for L2 grammatical analysis with LLMs
Stefano Bannò, Penny Karanasou, Kate Knill et al. (+1 more)
Evaluating the grammatical competence of second
language (L2) learners is essential both for providing targeted feedback and for assessing proficiency. To achieve this, we propose a novel framework leveraging the English Grammar Profile (EGP), a taxonomy of grammatical constructs mapped to the proficiency levels of the Common European Framework of Reference (CEFR), to detect learners' attempts at grammatical constructs and classify them as successful or unsuccessful. This detection can then be used to provide fine-grained feedback. Moreover, the grammatical constructs are used as predictors of proficiency assessment by using automatically detected attempts as predictors of holistic CEFR proficiency. For the selection of grammatical constructs derived from the EGP, rule-based and LLM-based classifiers are compared. We show that LLMs outperform rule-based methods on semantically and pragmatically nuanced constructs, while rule-based approaches remain competitive for constructs that rely purely on morphological or syntactic features and do not require semantic interpretation. For proficiency assessment, we evaluate both rule-based and hybrid pipelines and show that a hybrid approach combining a rule-based pre-filter with an LLM consistently yields the strongest performance. Since our framework operates on pairs of original learner sentences and their corrected counterparts, we also evaluate a fully automated pipeline using automatic grammatical error correction. This pipeline closely approaches the performance of semi-automated systems based on manual corrections, particularly for the detection of successful attempts at grammatical constructs. Overall, our framework emphasises learners' successful attempts in addition to unsuccessful ones, enabling positive, formative feedback and providing actionable insights into grammatical development.
Read the full abstract ▾
All authors Stefano Bannò, Penny Karanasou, Kate Knill, Mark Gales