Papers TriviaQA
“TriviaQA” 태그가 달린 논문 124편 · 필터 해제
Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostly unexplored. In this paper, we propose …
In-Context LearningNatural QuestionsRAGRetrieval+2GenKI: Enhancing Open-Domain Question Answering with Knowledge Integration and Controllable Generation in Large Language Models
Open-domain question answering (OpenQA) represents a cornerstone in natural language processing (NLP), primarily focused on extracting answers from unstructured textual data. With the rapid advancements in Large Language…
Open-Domain Question AnsweringPassage RetrievalQuestion AnsweringRetrieval+1HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation
Retrieval-Augmented Generation (RAG) encounters efficiency challenges when scaling to massive knowledge bases while preserving contextual relevance. We propose Hash-RAG, a framework that integrates deep hashing technique…
ChunkingDeep HashingPrompt EngineeringRAG+3Semantic Caching of Contextual Summaries for Efficient Question-Answering with Language Models
Large Language Models (LLMs) are increasingly deployed across edge and cloud platforms for real-time question-answering and retrieval-augmented generation. However, processing lengthy contexts in distributed systems incu…
Question AnsweringRetrievalRetrieval-augmented GenerationTriviaQADYNAMAX: Dynamic computing for Transformers and Mamba based architectures
Early exits (EEs) offer a promising approach to reducing computational costs and latency by dynamically terminating inference once a satisfactory prediction confidence on a data sample is achieved. Although many works in…
MambaTriviaQATruthfulQAShED-HD: A Shannon Entropy Distribution Framework for Lightweight Hallucination Detection on Edge Devices
Large Language Models (LLMs) have demonstrated impressive capabilities on a broad array of NLP tasks, but their tendency to produce hallucinations$\unicode{x2013}$plausible-sounding but factually incorrect content$\unico…
HallucinationTriviaQACacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation
Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g.,…
Natural QuestionsRetrievalRetrieval-augmented GenerationText Generation+1Cost-Saving LLM Cascades with Early Abstention
LLM cascades deploy small LLMs to answer most queries, limiting the use of large and expensive LLMs to difficult queries. This approach can significantly reduce costs without impacting performance. However, risk-sensitiv…
GSM8KMMLUOverall - TestTriviaQA+1Self-Training Large Language Models for Tool-Use Without Demonstrations
Large language models (LLMs) remain prone to factual inaccuracies and computational errors, including hallucinations and mistakes in mathematical reasoning. Recent work augmented LLMs with tools to mitigate these shortco…
GSM8KMathematical ReasoningQuestion AnsweringTriviaQAVision-centric Token Compression in Large Language Model
Real-world applications are stretching context windows to hundreds of thousand of tokens while Large Language Models (LLMs) swell from billions to trillions of parameters. This dual expansion send compute and memory cost…
In-Context LearningLanguage ModelingLanguage ModellingLarge Language Model+2ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval
Retrieval-Augmented Generation (RAG) models have drawn considerable attention in modern open-domain question answering. The effectiveness of RAG depends on the quality of the top retrieved documents. However, conventiona…
Language ModelingLanguage ModellingLarge Language ModelOpen-Domain Question Answering+6Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation
Open-domain Question Answering (QA) has garnered substantial interest by combining the advantages of faithfully retrieved passages and relevant passages generated through Large Language Models (LLMs). However, there is a…
Open-Domain Question AnsweringQuestion AnsweringRerankingRe-Ranking+1DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering
This paper proposes a novel approach to develop an open-domain and long-form Over-The-Top (OTT) Question-Answering (QA) dataset, DragonVerseQA, specifically oriented to the fantasy universe of "House of the Dragon" and "…
ArticlesFormNatural QuestionsQuestion Answering+3Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity
Evaluating the importance of different layers in large language models (LLMs) is crucial for optimizing model performance and interpretability. This paper first explores layer importance using the Activation Variance-Spa…
Contrastive LearningHallucinationLanguage ModelingLanguage Modelling+5Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI
In this paper, we present a dynamic semantic clustering approach inspired by the Chinese Restaurant Process, aimed at addressing uncertainty in the inference of Large Language Models (LLMs). We quantify uncertainty of an…
Conformal PredictionPredictionQuestion AnsweringTriviaQA+1Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation
Recent advances in large language model (LLM) training have highlighted the need for diverse, high-quality instruction data. Recently, many works are exploring synthetic data generation using LLMs. However, they primaril…
GSM8KLanguage ModelingLanguage ModellingLarge Language Model+4KV Prediction for Improved Time to First Token
Inference with transformer-based language models begins with a prompt processing step. In this step, the model generates the first output token and stores the KV cache needed for future generation steps. This prompt proc…
Code CompletionCPUHumanEvalPrediction+1Exploring Hint Generation Approaches in Open-Domain Question Answering
Automatic Question Answering (QA) systems rely on contextual information to provide accurate answers. Commonly, contexts are prepared through either retrieval-based or generation-based methods. The former involves retrie…
Hint GenerationOpen-Domain Question AnsweringQuestion AnsweringRetrieval+1SFR-RAG: Towards Contextually Faithful LLMs
Retrieval Augmented Generation (RAG), a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance, has emerged as a pivotal area in generative AI…
counterfactualHallucinationInstruction FollowingRAG+2FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection
Open Domain Question Answering (ODQA) has been advancing rapidly in recent times, driven by significant developments in dense passage retrieval and pretrained language models. Current models typically incorporate the FiD…
Answer GenerationDecoderNatural QuestionsOpen-Domain Question Answering+4