3834 papers
This paper presents the first comprehensive evaluation of parameter-efficient fine-tuning (PEFT) for multitask code analysis, demonstrating that a single shared PEFT module can match or surpass full fine-tuning performance while significantly reducing computational and storage costs, provided that tasks are strategically grouped based on factors like complementarity and stability.
This paper proposes Targeted Reasoning Unlearning (TRU), a novel framework that utilizes a reasoning-based unlearning target to guide models in precisely removing specific undesirable knowledge while preserving general capabilities and enhancing robustness against attacks.
This paper introduces AraModernBERT, an Arabic adaptation of the ModernBERT encoder that leverages transtokenized initialization and native long-context modeling up to 8,192 tokens to achieve significant improvements in both language modeling and downstream discriminative tasks.
MoE-SpAc is an efficient inference framework for Mixture-of-Experts models on heterogeneous edge devices that repurposes speculative decoding as a predictive sensor for memory management, achieving significant throughput improvements through dynamic workload balancing and asynchronous execution.
This empirical study demonstrates that large language models exhibit a Dunning-Kruger-like cognitive bias, where poorly performing models display significantly higher overconfidence and worse calibration than their more accurate counterparts.
This paper quantifies hallucinations in medical textbook-based QA by demonstrating that LLaMA-70B-Instruct hallucinated in nearly 20% of answers despite high plausibility, and found that lower hallucination rates generally correlate with higher clinician-rated usefulness across models.
This paper proposes a closed-loop framework that optimizes Large Language Model-driven Feature Transformation by evolving and selecting diverse, task-verified transformation trajectories via chain-of-thought reasoning, thereby outperforming existing methods in generating effective feature operators for downstream predictive tasks.
This paper presents a pipeline that bridges mechanistic interpretability and natural language explanations by identifying causally important attention heads in GPT-2 Small, generating high-quality explanations via LLMs, and evaluating their faithfulness to reveal that while explanations can be sufficient, they often lack comprehensiveness due to distributed backup mechanisms.
The paper introduces the System Hallucination Scale (SHS), a lightweight, human-centered psychometric instrument validated by 210 participants to rapidly evaluate Large Language Models' hallucination-related behaviors from a user perspective, distinct from automatic detection metrics.
This paper proposes a two-stage architecture combining LLaMA-3.1-8B-Instruct for NDA segmentation and a fine-tuned Legal-Roberta-Large for clause classification, achieving high precision (ROUGE F1 of 0.95 and weighted F1 of 0.85) to automate the analysis of complex Non-Disclosure Agreements.
This paper introduces PoultryLeX-Net, a domain-adaptive dual-stream transformer framework enhanced with poultry-specific lexicons and topic modeling, which significantly outperforms existing baseline models in accurately analyzing stakeholder sentiment within the global poultry industry.
This paper introduces TAMUSA-Chat, a research-oriented framework that enables academic institutions to build responsible, domain-adapted conversational AI systems through supervised fine-tuning, retrieval-augmented generation, and systematic evaluation, while providing a publicly available codebase to support reproducible experimentation and ethical deployment.
This paper introduces the Contextual Emotional Inference (CEI) Benchmark, a dataset of 300 human-validated scenarios designed to evaluate large language models' ability to infer intended meaning beyond literal semantics by navigating ambiguous utterances across diverse power dynamics and pragmatic subtypes.
This paper evaluates adjective-noun compositionality in large language models using both functional and representational approaches, revealing a significant divergence where models successfully develop compositional internal representations but fail to consistently translate them into functional task success.
This paper demonstrates through controlled experiments that a human-in-the-loop approach significantly outperforms iterative chain-of-thought prompting in improving behavioral interview answer quality, offering superior gains in confidence and authenticity with fewer iterations by prioritizing context availability over computational resources.
This study evaluates the robustness and pedagogical safety of offline large language models for Turkish heritage language education using a custom anomaly suite, finding that reasoning-oriented models in the 8B–14B parameter range offer the optimal balance between cost and safety while demonstrating that anomaly resistance is not strictly dependent on model scale.
This study refutes the claim that newer AI models have lost empathy, demonstrating through clinical assessment that while empathetic responses remain statistically consistent across generations, users' perception of "lost empathy" actually stems from a significant shift toward heightened crisis detection and altered safety postures that make the models appear more intrusive during vulnerable moments.
This paper presents an automated evaluation framework using semantic and sentiment analysis to assess Mandarin-to-English machine translation across news and literary texts, revealing that while LLMs like GPT-4o and DeepSeek excel in news translation and semantic conservation, they still struggle with preserving cultural subtleties, classical references, and figurative expressions in literary works.
This paper presents a retrieval-augmented language assistant designed to support unmanned aircraft safety assessments and regulatory compliance by grounding responses in authoritative sources to ensure traceable, auditable, and citation-driven decision support without replacing expert judgment.
This paper introduces LatamQA, a geographically informed sociocultural bias dataset of over 26,000 multilingual multiple-choice questions derived from Wikidata and Wikipedia, which reveals that current large language models exhibit significant performance disparities across Latin American countries, favoring Iberian Spanish culture and their original training languages.