939 papers
This paper introduces LoReSpeech, a low-resource speech-to-speech translation corpus constructed by aligning short collaborative recordings (LoReASR) with long-form audio using tools like MFA, aiming to advance multilingual ASR, direct speech translation, and linguistic preservation for underrepresented languages.
This paper establishes a formal mathematical connection between Correspondence Analysis (CA) and PMI-based word embeddings, introducing ROOT-CA and ROOTROOT-CA variants that empirically outperform standard PMI methods and achieve competitive results with BERT across multiple benchmarks.
This paper introduces X-GS, an extensible open framework that unifies 3D Gaussian Splatting with downstream multimodal models through a real-time, semantically enriched pipeline capable of processing unposed video streams for tasks like object detection and zero-shot captioning.
This paper introduces CyberThreat-Eval, an expert-annotated benchmark derived from real-world Cyber Threat Intelligence workflows that addresses the limitations of existing evaluations by assessing Large Language Models across the full triage-to-reporting pipeline using analyst-centric metrics, revealing significant gaps in current models' ability to handle nuanced, actionable security insights.
This paper introduces TA-Mem, a novel framework that enhances long-term conversational QA by employing tool-augmented autonomous agents to adaptively extract structured memory and dynamically select retrieval strategies, thereby overcoming the limitations of static similarity-based methods and achieving superior performance on the LoCoMo dataset.
This paper introduces AgentGEO, a diagnostic framework that identifies specific citation failure modes in Generative Engine Optimization and applies targeted, iterative repairs to achieve over 40% relative improvement in citation rates while modifying minimal content.
This paper systematically evaluates four Contrastive Decoding strategies across diverse Large Audio Language Models, identifying Audio-Aware and Audio Contrastive Decoding as most effective while introducing a Transition Matrix framework to demonstrate that these methods successfully rectify specific error patterns like false audio absence claims but fail to correct flawed reasoning or confident misassertions.
This paper introduces CREATE, a novel benchmark designed to evaluate large language models' associative creativity by measuring their ability to generate diverse and specific conceptual connections, revealing that while frontier models outperform others, current thinking and prompting strategies offer only limited improvements on this complex task.
This survey provides a comprehensive examination of model merging in the era of large language models by introducing the FUSE taxonomy to systematically analyze theoretical foundations, algorithmic strategies, diverse applications, and the supporting ecosystem, while identifying key challenges for future research.
This paper reveals that enabling reasoning in large language models significantly enhances the recall of simple factual knowledge through two mechanisms—computational buffering and factual priming—while also demonstrating that hallucinating intermediate facts during this process increases final answer errors, a finding that can be leveraged to improve model accuracy by prioritizing hallucination-free reasoning trajectories.
Through large-scale survey experiments involving over 19,000 participants, this study demonstrates that frontier large language models generally outperform standard political advertisements in persuasiveness, with significant performance variations across models and a model-dependent impact of information-based prompting strategies.
This paper introduces DoWhatISay (DOWIS), a multilingual dataset of human-recorded spoken and written prompts designed to evaluate Speech Large Language Models under realistic spoken instruction conditions, revealing that text prompts generally outperform spoken ones except in tasks requiring speech output.
This paper argues that reading time is better predicted by simple n-gram statistics than by complex transformer models, demonstrating that neural language models whose predictions align closely with n-gram probabilities are the most effective at correlating with eye-tracking reading time metrics.
This paper proposes using Chow-Liu trees to optimize chunk ordering in Chain-of-Agents frameworks, demonstrating that a breadth-first traversal of the learned dependency structure significantly reduces information loss and improves reasoning accuracy on long-context benchmarks compared to standard ordering methods.
One-Eval is an agentic system that automates the end-to-end evaluation of large language models by converting natural-language requests into traceable, customizable workflows through integrated components for benchmark planning, dataset resolution, and decision-oriented reporting, thereby reducing manual effort and enhancing reproducibility.
This paper presents an updated, combined English-German corpus of European Parliament speeches, translations, and interpretations with refined metadata and new information-theoretic annotations, designed to support research on language variation, translationese, and the prediction of disfluencies in interpreting using probabilistic models.
This paper introduces FoodOntoRAG, a novel, fine-tuning-free pipeline that leverages retrieval-augmented generation and multi-agent reasoning to achieve robust, ontology-agnostic food entity linking that remains accurate despite ontology drift while providing interpretable justifications.
This paper evaluates four Large Language Models within a Retrieval-Augmented Generation system for food and nutrition data, finding that while they effectively translate natural language queries into structured metadata filters to reduce manual effort, their reliability diminishes when handling complex queries involving constraints that exceed the representational scope of the underlying metadata.
This paper proposes a multi-perspective framework for estimating recipe similarity by integrating semantic, lexical, and domain-specific nutritional data, which was validated by domain experts to identify the most influential factors in human decision-making for applications in personalized nutrition and automated recipe generation.
This keynote presentation at ECIR 2025 explores the critical interplay between a language model's internal parametric knowledge and external contextual information, focusing on diagnostic methods to identify knowledge conflicts and strategies to improve the model's ability to utilize retrieved context effectively.