1077 papers
This study benchmarks the Motivational Interviewing competence of ten large language models against human therapists using the MITI framework, finding that top-performing models achieve good proficiency in real-world clinical transcripts and are difficult for psychiatrists to distinguish from human responses, suggesting their viability for expanding counseling in low-resource settings.
This paper addresses the limitations of hierarchical models in Rhetorical Role Labeling by proposing prototype-based methods that integrate local context with global semantic representations, introducing the new SCOTUS-Law dataset, and demonstrating consistent performance improvements across legal, medical, and scientific domains.
This paper evaluates the effectiveness of large language models in delivering Cognitive Behavioral Therapy by comparing generation-only and retrieval-augmented approaches against professional transcripts, finding that while LLMs can mimic CBT dialogues, they currently struggle with conveying empathy and maintaining therapeutic consistency.
This paper evaluates the feasibility and limitations of using LLM-driven agents to autonomously audit dark patterns in CCPA data rights request workflows across 456 websites, assessing their ability to navigate interfaces, classify manipulative designs, and identify failure conditions.
This paper introduces CzechTopic, a human-annotated benchmark for zero-shot topic localization in historical Czech documents that evaluates diverse large language models and fine-tuned BERT-based models, revealing significant performance variability among LLMs while demonstrating that smaller distilled models remain competitive.
This paper presents IROSA, a novel framework that leverages pre-trained large language models to enable open-vocabulary, safe, and interpretable robot skill adaptation for industrial tasks through a tool-based architecture that avoids direct model-to-robot interaction or fine-tuning.
This paper proposes a neuro-symbolic multi-agent system that leverages hypernym-hyponym semantic relations to extract information from Cyber Threat Intelligence reports and automatically generate CLIPS-based firewall rules, demonstrating superior performance in threat mitigation compared to baseline approaches.
This paper proposes an anonymous benchmarking method to expose the bias in current role-playing evaluations caused by character name exposure and demonstrates that incorporating self-generated personality traits effectively enhances model performance under these fairer conditions.
This paper evaluates the efficacy of using large language models as judges for French medical open-ended question answering, demonstrating that while performance varies by generator, lightweight adaptation of compact models via supervised fine-tuning and GRPO significantly improves alignment with expert annotations and reduces generator bias.
This paper proposes an activation-based monitoring method using sparse autoencoders and linear classifiers to detect emergent reward-hacking behavior in fine-tuned large language models during generation, demonstrating that internal activation patterns provide reliable, early, and generalizable signals of misalignment that often precede or persist beyond final output analysis.
This paper evaluates how the integration of Large Language Models into machine translation workflows impacts the reliability of established source-side difficulty and candidate-side quality estimation paradigms, using a unique multi-candidate post-editing dataset to demonstrate that while LLMs alter the effectiveness of traditional prediction methods, they also mitigate prior challenges in document-level translation.
This paper introduces FINEST, a fine-grained evaluation taxonomy that categorizes errors in LLM responses to sensitive topics into Content, Logic, and Appropriateness, demonstrating that using this framework to guide score-based improvements significantly enhances both the safety and helpfulness of model outputs.
This paper demonstrates that while parameter-efficient reinforcement learning with verifiable rewards significantly improves a compact language model's performance on beam statics, it primarily induces anisotropic procedural template matching rather than robust, transferable physical reasoning, highlighting the need for structured scaffolding to achieve genuine scientific understanding.
This paper introduces VietNormalizer, a lightweight, zero-dependency Python library that provides a comprehensive, rule-based pipeline for normalizing diverse Vietnamese text elements—such as numbers, dates, currency, and foreign terms—into pronounceable forms for TTS and NLP applications.
This paper investigates the social competence of 17 large language models using an extensive set of False Belief Test variants, revealing that while scaling improves performance, the explicit mention of mental states triggers a cross-over effect rooted in pre-training stereotypes that can be causally isolated via vector steering.
This paper introduces the Disentangled Code Attribution Network (DCAN), a novel framework that leverages contrastive learning to disentangle source-specific stylistic fingerprints from semantic content, enabling accurate identification of the specific Large Language Model responsible for generating code snippets across multiple programming languages.
This paper evaluates eleven major Large Language Models across eight languages and reveals systematic biases where they are more likely to endorse limitations on Economic, Social, and Cultural rights than Political and Civil rights, exhibit significant cross-linguistic variations, and show high susceptibility to prompt-based steering.
This paper demonstrates that improvements in multilingual and visually rich retrieval-augmented generation benchmarks are primarily driven by better document representation and preprocessing rather than advanced retrieval mechanisms, urging the field to adopt decomposed evaluation metrics to accurately attribute progress.
The paper introduces Memex, an indexed experience memory system optimized via a reinforcement learning framework (MemexRL) that enables long-horizon LLM agents to maintain high decision quality by storing full-fidelity interactions externally and retrieving them on demand, thereby overcoming context window limitations without the information loss inherent in traditional summarization methods.
This paper proposes a pipeline that leverages large language models to generate documents, extract and canonicalize events, and apply causal discovery methods to produce an inspectable set of plausible causal hypotheses reflecting the models' internal knowledge, rather than guaranteeing real-world causality.