Papers Informativeness
“Informativeness” 태그가 달린 논문 735편 · 필터 해제
Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation
Large language models (LLMs) incorporated with Retrieval-Augmented Generation (RAG) have demonstrated powerful capabilities in generating counterspeech against misinformation. However, current studies rely on limited evi…
InformativenessMisinformationRAGRetrieval+1LumiCRS: Asymmetric Contrastive Prototype Learning for Long-Tail Conversational Movie Recommendation
Conversational recommender systems (CRSs) often suffer from an extreme long-tail distribution of dialogue data, causing a strong bias toward head-frequency blockbusters that sacrifices diversity and exacerbates the cold-…
DiversityFairnessInformativenessMovie Recommendation+1Dynamic Bandwidth Allocation for Hybrid Event-RGB Transmission
Event cameras asynchronously capture pixel-level intensity changes with extremely low latency. They are increasingly used in conjunction with RGB cameras for a wide range of vision-related applications. However, a major …
DeblurringInformativenessMulti-Preference Lambda-weighted Listwise DPO for Dynamic Preference Alignment
While large-scale unsupervised language models (LMs) capture broad world knowledge and reasoning capabilities, steering their behavior toward desired objectives remains challenging due to the lack of explicit supervision…
Informativenessreinforcement-learningReinforcement LearningWorld KnowledgeCuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems
Popular text-to-image (T2I) systems are trained on web-scraped data, which is heavily Amero and Euro-centric, underrepresenting the cultures of the Global South. To analyze these biases, we introduce CuRe, a novel and sc…
AttributeBenchmarkingInformativenessImage Reconstruction as a Tool for Feature Analysis
Vision encoders are increasingly used in modern applications, from vision-only models to multimodal systems such as vision-language models. Despite their remarkable success, it remains unclear how these architectures rep…
Contrastive LearningImage ReconstructionInformativenessInvestigating the Impact of Word Informativeness on Speech Emotion Recognition
In emotion recognition from speech, a key challenge lies in identifying speech signal segments that carry the most relevant acoustic variations for discerning specific emotions. Traditional approaches compute functionals…
Emotion RecognitionInformativenessLanguage ModelingLanguage Modelling+1Assumption-free stability for ranking problems
In this work, we consider ranking problems among a finite set of candidates: for instance, selecting the top-$k$ items among a larger list of candidates or obtaining the full ranking of all items in the set. These proble…
InformativenessERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation
Unsupervised keyphrase prediction has gained growing interest in recent years. However, existing methods typically rely on heuristically defined importance scores, which may lead to inaccurate informativeness estimation.…
InformativenessKeyphrase GenerationText RetrievalUnderstanding while Exploring: Semantics-driven Active Mapping
Effective robotic autonomy in unknown environments demands proactive exploration and precise understanding of both geometry and semantics. In this paper, we propose ActiveSGM, an active semantic mapping framework designe…
3DGSInformativenessUncertainty QuantificationDirected Homophily-Aware Graph Neural Network
Graph Neural Networks (GNNs) have achieved significant success in various learning tasks on graph-structured data. Nevertheless, most GNNs struggle to generalize to heterophilic neighborhoods. Additionally, many GNNs ign…
Graph Neural NetworkInformativenessLink PredictionNode ClassificationLimits of Disclosure in Search Markets
This paper examines competitive information disclosure in search markets with a mix of savvy consumers, who search costlessly, and inexperienced consumers, who face positive search costs. Savvy consumers incentivize trut…
InformativenessOASIS: Online Sample Selection for Continual Visual Instruction Tuning
In continual visual instruction tuning (CVIT) scenarios, where multi-modal data continuously arrive in an online streaming manner, training delays from large-scale data significantly hinder real-time adaptation. While ex…
InformativenessCIDRe: A Reference-Free Multi-Aspect Criterion for Code Comment Quality Measurement
Effective generation of structured code comments requires robust quality metrics for dataset curation, yet existing approaches (SIDE, MIDQ, STASIS) suffer from limited code-comment analysis. We propose CIDRe, a language-…
InformativenessTask-Oriented Low-Label Semantic Communication With Self-Supervised Learning
Task-oriented semantic communication enhances transmission efficiency by conveying semantic information rather than exact messages. Deep learning (DL)-based semantic communication can effectively cultivate the essential …
image-classificationImage ClassificationInformativenessSelf-Supervised Learning+1ICYM2I: The illusion of multimodal informativeness under missingness
Multimodal learning is of continued interest in artificial intelligence-based applications, motivated by the potential information gain from combining different types of data. However, modalities collected and curated du…
InformativenessPower-Law Decay Loss for Large Language Model Finetuning: Focusing on Information Sparsity to Enhance Generation Quality
During the finetuning stage of text generation tasks, standard cross-entropy loss treats all tokens equally. This can lead models to overemphasize high-frequency, low-information tokens, neglecting lower-frequency tokens…
Abstractive Text SummarizationInformativenessLanguage ModelingLanguage Modelling+4A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics
Large Language Models are essential coding assistants, yet their training is predominantly English-centric. In this study, we evaluate the performance of code language models in non-English contexts, identifying challeng…
InformativenessLaplace Sample Information: Data Informativeness Through a Bayesian Lens
Accurately estimating the informativeness of individual samples in a dataset is an important objective in deep learning, as it can guide sample selection, which can improve model efficiency and accuracy by removing redun…
InformativenessAdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference
Assessing Large Language Models (LLMs)' underlying value differences enables comprehensive comparison of their misalignment, cultural adaptability, and biases. Nevertheless, current value measurement datasets face the in…
Informativeness