Papers Natural Questions
“Natural Questions” 태그가 달린 논문 216편 · 필터 해제
When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control
Large language models can produce fluent answers when their factual support is weak. This paper introduces Chain-of-Self-Questioning (CoSQ), a prompt-only framework that makes answer commitment conditional on an explicit…
Natural QuestionsSame Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA
A retrieval-augmented QA system can return different answers after an index expansion even when its requested model identifier, prompt, retrieval policy, evidence depth, rendering, and exposed generation controls are hel…
Natural QuestionsFrom Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG
Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context lengthens the prompt, increasing prefill work, KV-cache fo…
Natural QuestionsStatic Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps
Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it unclear which findings transfer to modern engines with…
Natural QuestionsTabRank: Chain-of-Thought Distillation for Table Re-Rankers
The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval. Multi-stage retrieval systems rely heavily on rerankers to refine candidate lists produced by efficient …
Information RetrievalNatural QuestionsPassage RetrievalTable RetrievalRAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning
Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning: maliciously injected passages that manipulate retrieved evidence. …
Natural QuestionsSmartRAG: Native Graph-Based RAG for Mobile Device
Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets…
Natural QuestionsModel CompressionKnow Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) typically retrieves a fixed number of passages for every query. This is wasteful when the reader already knows the answer, and it can be harmful when irrelevant or partially relevant …
Natural QuestionsCONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation
Retrieval-augmented generation (RAG) has emerged as a pivotal technique for improving language models by incorporating external knowledge at inference time. As device-cloud collaborative inference makes it feasible to de…
Natural QuestionsGrounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG
As retrieval-augmented generation (RAG) systems scale, it becomes increasingly challenging to ensure faithful grounding in external evidence. Large language models may still prioritize parametric knowledge over retrieved…
Natural QuestionsSilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through …
Natural QuestionsUnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely optimized through a unified reinforcement …
Reinforcement LearningNatural QuestionsCode GenerationEnhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment
Metacognition-the ability to monitor one's own knowledge state, spot gaps, and autonomously fill them--remains largely absent from modern AI. Here, we present MetaKGEnrich, a fully automated pipeline that endows large la…
Natural QuestionsKnowledge GraphsPersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
We introduce PersonalAI 2.0 (PAI-2), a novel framework, designed to enhance large language model (LLM) based systems through integration of external knowledge graphs (KG). The proposed approach addresses key limitations …
Natural QuestionsKnowledge GraphsArchitecture Matters: Comparing RAG Systems under Knowledge Base Poisoning
Retrieval-Augmented Generation (RAG) systems are vulnerable to knowledge base poisoning, yet existing attacks have been evaluated almost exclusively against vanilla retrieve-then-generate pipelines. Architectures designe…
Adversarial RobustnessAdversarial AttackNatural QuestionsA Parametric Memory Head for Continual Generative Retrieval
Generative information retrieval (GenIR) consolidates retrieval into a single neural model that decodes document identifiers (docids) directly from queries. While this model-as-index paradigm offers architectural simplic…
parameter-efficient fine-tuningInformation RetrievalNatural QuestionsHow Hard Is Continuous Clustering? Lower Bounds from the Existential Theory of the Reals
This paper studies the computational difficulty of clustering problems that are defined directly on a continuous probability density. Rather than working with finite samples, we assume the density is given as a polynomia…
Natural QuestionsSample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End
Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi et al. (COLT 2025) introduced a PAC-learning framework for next-token generato…
Natural QuestionsPIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as outdated knowledge and the tendency to ge…
Natural QuestionsTest-Time Strategies for More Efficient and Accurate Agentic RAG
Retrieval-Augmented Generation (RAG) systems face challenges with complex, multihop questions, and agentic frameworks such as Search-R1 (Jin et al., 2025), which operates iteratively, have been proposed to address these …
Natural Questions