Searcharxiv⌕ Search

arXiv subjects

Farig Sadeque

Publications and source records attributed to Farig Sadeque.

At least 19 recordsLinked to original sources
arXiv2026

Below the Noise Floor: Bimodal Seed Collapse and Distinct Failure Modes in Small-Model Knowledge Distillation

Function routing -- selecting the correct API call from a fixed catalog given a natural-language request -- is a deployment problem where small students are attractive but knowledge distillation gains are typically reported single-seed, at scales where seed variance is unknown. On a 740-instance healthcare API routing task with a 1.5B Qwen student and a 20B teacher, we compare eight KD variants against supervised cross-entropy, using three to six seeds for key configurations. We find: (i) per-seed standard deviation ranges from 2.8 to 48.7 percentage points, swallowing every claimed KD gain below five points; (ii) three of seven KD variants exhibit bimodal collapse, with at least one in three to five seeds falling below 55% accuracy while the others train normally, and a fourth showing elevated variance; (iii) collapse has distinct modes -- wrong-function selection for ce_kd and ce_paraphrase, and a previously undocumented output-truncation mode for reasoning_kd, where the model emits reasoning but terminates before producing a function name (0.9% accuracy); (iv) only progressive_kd and rank_kd avoid collapse across observed seeds, with sigma <= 3.9 pp; (v) a naive cross-split +3.78 pp gain from input enrichment reverses to -2.70 pp under controlled within-split multi-seed re-testing. Single-seed evaluation is therefore unable to detect central failure modes in small-model KD.

cs.CL↗
arXiv2026

Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document Understanding

Evolving documents, such as laws, tax codes, and software documentation, are amended, replaced, and sometimes reverted over time, so a question has different correct answers at different dates. In contrast to encyclopedic knowledge, where an old fact is simply overwritten, an amendment is itself an official text that states what it replaces and when it takes effect, and the earlier version stays correct for its validity period. The central challenge is therefore version resolution, that is, identifying the version in force on the queried date. Existing temporal QA datasets treat time only as an annotation, so version resolution stays untested. We present TIDE, an expert-verified benchmark of 3,050 QA pairs over 644 official customs instruments issued between 1969 and 2025 by the Government of Bangladesh, covering eight task types over deeply code-mixed documents that are heterogeneous in layout and dated in two calendars. In addition, we evaluate nine recent LLMs under a single protocol across parametric, gold-context, and retrieval access, scored by a three-judge LLM council with a hard date gate separating correct meaning from correct time. The best macro-averaged accuracy is only 68.5%. Resolving a version from an implicit date reaches 59.7%, and detecting that the supplied version does not govern the query reaches only 26.7%. Models are more likely to find correct versions than to reject incorrect ones, and they tend to follow a confident parametric answer over the supplied authoritative text. All code and data are available at https://github.com/icsetepa44/TIDE

cs.AI↗
arXiv2026

Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation

Medical vision-language models still struggle to match radiologists' attention and to verbalize findings with explicit spatial grounding. We address this gap with a two-stage multimodal framework for chest X-ray interpretation built on the MIMIC-Eye dataset. In the first stage introduces a gaze-token classifier that fuses image patches, bounding-box masks, transcription embeddings, and radiologist fixations. A curriculum-scheduled, trust-calibrated composite loss supervises the gaze token, boosting both accuracy and spatial alignment. Adding fixation supervision raises AUC 4.4% and F1 13.3%, and Pearson correlation rises to 0.306, confirming clinically relevant focus. In stage 2, classifier predictions are translated into region-specific diagnostic sentences. Confidence-weighted keywords are extracted, mapped to 17 thoracic regions through an expert dictionary, and expanded with a prompted large language model, boosting clinical-term BERTScore and ROUGE scores over keyword baselines. All components are toggle-able for ablation, and the full pipeline is reproducible, offering a new benchmark for interpretable, gaze-aware chest-X-ray analysis. Integrating eye-tracking signals demonstrably enhances both diagnostic accuracy and the transparency of generated reports.

cs.CV↗
arXiv2026

BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language

Traditional retrieval-augmented generation (RAG) frameworks process documents without attending to their hierarchical structure, leading to poor performance, especially in low-resource languages such as Bengali. To address this, we propose a structure-aware RAG framework that models Bengali textbooks as hierarchical graphs and uses a contrastively trained graph neural network to retrieve a small set of relevant passages. These passages provide focused context for a large language model, enabling topic-specific multiple-choice question (MCQ) generation and in-domain answer prediction. Experimental results demonstrate that our framework outperforms strong dense retrieval baselines across retrieval metrics, produces more relevant MCQs, and achieves superior answer prediction accuracy.

cs.CL↗
arXiv2026

When Does Knowledge Distillation Hurt? Reliability-Aware Distillation for Low-Resource Language Summarization

Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined. On the BanSum Bangla summarization benchmark, we find that standard KD improves ROUGE-L by only +0.0003 over a cross-entropy baseline, and that approximately 51.3% of training samples are estimated to actively harm student validation loss under standard KD. We propose two complementary reliability-aware distillation methods. CHAD (Counterfactual Harm-Aware Distillation) measures per-sample KD usefulness via gradient alignment with the validation loss direction and trains a lightweight gate that generalizes this counterfactual judgment to the full training set. EWAD+CPDP combines token-level entropy-weighted adaptive distillation with a capacity-proportional geometric constraint from a second, vocabulary-incompatible teacher. On BanSum, both methods substantially outperform standard KD: CHAD by +0.0173 ROUGE-L and EWAD+CPDP by +0.0219 ROUGE-L, where standard KD itself improves ROUGE-L by only +0.0003; despite using only 60M parameters, both outperform a fine-tuned Qwen 2.5-3B model (50x larger). We further evaluate the stronger method, EWAD+CPDP, across 15 typologically diverse XL-Sum languages organised into three sets, beating the CE-only baseline on 10/15 languages; gains are most reliable where the two teachers contribute complementary signal, and weakest where they have saturated or jointly weak target-language coverage. We release code and trained models to support reproducibility and further research on selective distillation.

cs.CL↗
arXiv2026

Contaminated Collaboration: Measuring Gender Bias Transfer in LLM-Assisted Student Writing

Gender bias in LLMs has been studied extensively in model outputs, with biased prompts shown to amplify stereotyped generations. Whether such bias propagates into text produced by humans who use these systems, however, remains underexplored. We investigate whether gender bias in an LLM writing assistant transfers into career plan essays written by students. We first verify that a gender-biased prompt induces gender-differentiated language in LLM-generated essays, while a neutral prompt does not. We then recruited participants (N = 123) in a controlled environment to write career plan essays for paired biographical profiles differing only in gender under three conditions: no AI assistance, neutral LLM assistance, or gender-biased LLM assistance. Students in the biased condition produced essays with a significantly larger agentic gap and more gender-stereotypic occupation suggestions than those in the control and neutral conditions. Our results also reveal that this bias transfer is asymmetric: agency is suppressed in female-target essays while male-target writing remains largely unaffected. Our findings highlight the risk of bias propagation in AI-assisted writing, calling for fairness-aware design in educational AI tools.

cs.CL↗
arXiv2026

A Survey on Agentic Security: Applications, Threats and Defenses

LLM-based agents are now used throughout cybersecurity. While these agents facilitate powerful and autonomous security applications, their autonomy opens up new attack surfaces, and the security community is actively building defenses to secure them. Yet the literature on this subject has grown quickly and unevenly. Existing surveys treat applications, threats, and defenses in isolation, leaving no unified account of how an agent's capabilities, vulnerabilities, and countermeasures interconnect. In this work we present the first holistic survey of the agentic security landscape, structuring the field around the fundamental pillars of Applications, Threats and Defenses. We provide a comprehensive taxonomy of over 260 papers, explaining how agents are used in downstream cybersecurity applications, inherent threats to agentic systems, and countermeasures designed to protect them. In addition, we provide detailed pillar-specific and cross-cutting analyses that show the security-lifecycle coverage of agentic applications, comparison between red-teaming and blue-teaming agents, and the adversarial use of red-teaming applications. On the threat side, we analyze the entry points and agent-loop stages that attacks target, their specificity to the agentic setting, and the threat models they assume. On the defense side, we analyze the prevailing defense strategies, their cost and security trade-offs, and where in the agent lifecycle they are deployed. We further map which defenses cover which attack classes and chart trends in agent architecture, backbone model usage, data modality coverage, and the growth of attack and defense research over time. Taken together, these findings indicate that agentic systems are structurally fragile by default and that securing them will require defenses that span the full agent lifecycle rather than single-layer fixes.

cs.CL↗
arXiv2026

Representation-Aware Unlearning via Activation Signatures: From Suppression to Entity-Signature Erasure

Entity-level unlearning is usually evaluated by what a model says: whether it stops naming the target, refuses a query, or shifts a Truth Ratio distribution. These output-level tests, however, do not show whether a subject's internal representation has been attenuated. We introduce the Entity Representation Unlearning Framework (ERUF), a representation-aware framework that mines subject-specific activation signatures, suppresses the corresponding activation direction, and distills the behavior into LoRA parameters. Among evaluated baselines, ERUF is the only method that jointly achieves surface-level suppression, internal attenuation, and utility preservation. On TOFU forget10, ERUF achieves FQ = 0.99 and MU = 0.62, matching reported oracle utility while approaching oracle forget quality. Across most standard foundation-model settings, ERUF maintains low leakage and low internal target activation, with SMR between 0.00% and 1.10%, EL10 below 0.06, and utility drift below 3%. On Llama-3.1-8B, adversarial entity recovery falls from 63.89% to 20.15%, while name-agnostic recovery decreases by 72.7% to 77.4%. Joint surface/internal diagnostics further reveal scale-dependent behavior in reasoning-prior models that surface metrics alone would miss. We interpret these results as operational evidence of representation-level attenuation, not as a formal guarantee of irreversible deletion.

cs.CL↗
arXiv2026

Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models

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.

cs.CL↗
arXiv2026

Enhancing Mental Health Counseling Support in Bangladesh using Culturally-Grounded Knowledge

Large language models (LLMs) show promise in generating supportive responses for mental health and counseling applications. However, their responses often lack cultural sensitivity, contextual grounding, and clinically appropriate guidance. This work addresses the gap of how to systematically incorporate domain-specific, clinically validated knowledge into LLMs to improve counseling quality. We utilize and compare two approaches, retrieval-augmented generation (RAG) and a knowledge graph (KG)-based method, designed to support para-counselors. Our KG is constructed manually and clinically validated, capturing causal relationships between stressors, interventions, and outcomes, with contributions from multidisciplinary people. We evaluated multiple LLMs in both settings using BERTScore F1 and SBERT cosine similarity, as well as human evaluation across five metrics, which is designed to directly measure the effectiveness of counseling beyond similarity at the surface level. The results show that KG-based approaches consistently improve contextual relevance, clinical appropriateness, and practical usability compared to RAG alone, demonstrating that structured, expert-validated knowledge plays a critical role in addressing LLMs limitations in counseling tasks.

cs.AI↗
arXiv2026

Benchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIF

Large language models (LLMs) frequently exhibit performance biases against regional dialects of low-resource languages. However, frameworks to quantify these disparities remain scarce. We propose a two-phase framework to evaluate dialectal bias in LLM question-answering across nine Bengali dialects. First, we translate and gold-label standard Bengali questions into dialectal variants adopting a retrieval-augmented generation (RAG) pipeline to prepare 4,000 question sets. Since traditional translation quality evaluation metrics fail on unstandardized dialects, we evaluate fidelity using an LLM-as-a-judge, which human correlation confirms outperforms legacy metrics. Second, we benchmark 19 LLMs across these gold-labeled sets, running 68,395 RLAIF evaluations validated through multi-judge agreement and human fallback. Our findings reveal severe performance drops linked to linguistic divergence. For instance, responses to the highly divergent Chittagong dialect score 5.44/10, compared to 7.68/10 for Tangail. Furthermore, increased model scale does not consistently mitigate this bias. We contribute a validated translation quality evaluation method, a rigorous benchmark dataset, and a Critical Bias Sensitivity (CBS) metric for safety-critical applications.

cs.CL↗
arXiv2026

AI as Teammate or Tool? A Review of Human-AI Interaction in Decision Support

The integration of Artificial Intelligence (AI) necessitates determining whether systems function as tools or collaborative teammates. In this study, by synthesizing Human-AI Interaction (HAI) literature, we analyze this distinction across four dimensions: interaction design, trust calibration, collaborative frameworks and healthcare applications. Our analysis reveals that static interfaces and miscalibrated trust limit AI efficacy. Performance hinges on aligning transparency with cognitive workflows, yet a fluency trap often inflates trust without improving decision-making. Consequently, an overemphasis on explainability leaves systems largely passive. Our findings show that current AI systems remain largely passive due to an overreliance on explainability-centric designs and that transitioning AI to an active teammate requires adaptive, context-aware interactions that support shared mental models and the dynamic negotiation of authority between humans and AI.

cs.HC↗
arXiv2025

A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs

Translating from a standard language to its regional dialects is a significant NLP challenge due to scarce data and linguistic variation, a problem prominent in the Bengali language. This paper proposes and compares two novel RAG pipelines for standard-to-dialectal Bengali translation. The first, a Transcript-Based Pipeline, uses large dialect sentence contexts from audio transcripts. The second, a more effective Standardized Sentence-Pairs Pipeline, utilizes structured local\_dialect:standard\_bengali sentence pairs. We evaluated both pipelines across six Bengali dialects and multiple LLMs using BLEU, ChrF, WER, and BERTScore. Our findings show that the sentence-pair pipeline consistently outperforms the transcript-based one, reducing Word Error Rate (WER) from 76\% to 55\% for the Chittagong dialect. Critically, this RAG approach enables smaller models (e.g., Llama-3.1-8B) to outperform much larger models (e.g., GPT-OSS-120B), demonstrating that a well-designed retrieval strategy can be more crucial than model size. This work contributes an effective, fine-tuning-free solution for low-resource dialect translation, offering a practical blueprint for preserving linguistic diversity.

cs.CL↗
arXiv2025

Bridging Human and Model Perspectives: A Comparative Analysis of Political Bias Detection in News Media Using Large Language Models

Detecting political bias in news media is a complex task that requires interpreting subtle linguistic and contextual cues. Although recent advances in Natural Language Processing (NLP) have enabled automatic bias classification, the extent to which large language models (LLMs) align with human judgment still remains relatively underexplored and not yet well understood. This study aims to present a comparative framework for evaluating the detection of political bias across human annotations and multiple LLMs, including GPT, BERT, RoBERTa, and FLAN. We construct a manually annotated dataset of news articles and assess annotation consistency, bias polarity, and inter-model agreement to quantify divergence between human and model perceptions of bias. Experimental results show that among traditional transformer-based models, RoBERTa achieves the highest alignment with human labels, whereas generative models such as GPT demonstrate the strongest overall agreement with human annotations in a zero-shot setting. Among all transformer-based baselines, our fine-tuned RoBERTa model acquired the highest accuracy and the strongest alignment with human-annotated labels. Our findings highlight systematic differences in how humans and LLMs perceive political slant, underscoring the need for hybrid evaluation frameworks that combine human interpretability with model scalability in automated media bias detection.

cs.CL↗
arXiv2025

BNLI: A Linguistically-Refined Bengali Dataset for Natural Language Inference

Despite the growing progress in Natural Language Inference (NLI) research, resources for the Bengali language remain extremely limited. Existing Bengali NLI datasets exhibit several inconsistencies, including annotation errors, ambiguous sentence pairs, and inadequate linguistic diversity, which hinder effective model training and evaluation. To address these limitations, we introduce BNLI, a refined and linguistically curated Bengali NLI dataset designed to support robust language understanding and inference modeling. The dataset was constructed through a rigorous annotation pipeline emphasizing semantic clarity and balance across entailment, contradiction, and neutrality classes. We benchmarked BNLI using a suite of state-of-the-art transformer-based architectures, including multilingual and Bengali-specific models, to assess their ability to capture complex semantic relations in Bengali text. The experimental findings highlight the improved reliability and interpretability achieved with BNLI, establishing it as a strong foundation for advancing research in Bengali and other low-resource language inference tasks.

cs.CL↗
arXiv2025

Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?

Conventional research on speech recognition modeling relies on the canonical form for most low-resource languages while automatic speech recognition (ASR) for regional dialects is treated as a fine-tuning task. To investigate the effects of dialectal variations on ASR we develop a 78-hour annotated Bengali Speech-to-Text (STT) corpus named Ben-10. Investigation from linguistic and data-driven perspectives shows that speech foundation models struggle heavily in regional dialect ASR, both in zero-shot and fine-tuned settings. We observe that all deep learning methods struggle to model speech data under dialectal variations but dialect specific model training alleviates the issue. Our dataset also serves as a out of-distribution (OOD) resource for ASR modeling under constrained resources in ASR algorithms. The dataset and code developed for this project are publicly available

cs.CL↗
arXiv2025

RegSpeech12: A Regional Corpus of Bengali Spontaneous Speech Across Dialects

The Bengali language, spoken extensively across South Asia and among diasporic communities, exhibits considerable dialectal diversity shaped by geography, culture, and history. Phonological and pronunciation-based classifications broadly identify five principal dialect groups: Eastern Bengali, Manbhumi, Rangpuri, Varendri, and Rarhi. Within Bangladesh, further distinctions emerge through variation in vocabulary, syntax, and morphology, as observed in regions such as Chittagong, Sylhet, Rangpur, Rajshahi, Noakhali, and Barishal. Despite this linguistic richness, systematic research on the computational processing of Bengali dialects remains limited. This study seeks to document and analyze the phonetic and morphological properties of these dialects while exploring the feasibility of building computational models particularly Automatic Speech Recognition (ASR) systems tailored to regional varieties. Such efforts hold potential for applications in virtual assistants and broader language technologies, contributing to both the preservation of dialectal diversity and the advancement of inclusive digital tools for Bengali-speaking communities. The dataset created for this study is released for public use.

cs.CL↗
arXiv2025

From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge

Recent progress in NLP research has demonstrated remarkable capabilities of large language models (LLMs) across a wide range of tasks. While recent multilingual benchmarks have advanced cultural evaluation for LLMs, critical gaps remain in capturing the nuances of low-resource cultures. Our work addresses these limitations through a Bengali Language Cultural Knowledge (BLanCK) dataset including folk traditions, culinary arts, and regional dialects. Our investigation of several multilingual language models shows that while these models perform well in non-cultural categories, they struggle significantly with cultural knowledge and performance improves substantially across all models when context is provided, emphasizing context-aware architectures and culturally curated training data.

cs.CL↗