Buchumschlag

Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Yu, Sangwon, Kim, Ik-hwan, Song, Jongyoon, Lee, Saehyung, Park, Junsung, Yoon, Sungroh
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge
von: Song, Jongyoon, et al.
Veröffentlicht: (2025)

Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination
von: Song, Jongyoon, et al.
Veröffentlicht: (2024)

Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP
von: Park, Junsung, et al.
Veröffentlicht: (2025)

Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach
von: Lee, Saehyung, et al.
Veröffentlicht: (2024)

Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis
von: Mok, Jisoo, et al.
Veröffentlicht: (2025)

Knowledge Integration Decay in Search-Augmented Reasoning of Large Language Models
von: Yu, Sangwon, et al.
Veröffentlicht: (2026)

Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering
von: Kim, Ik-hwan, et al.
Veröffentlicht: (2026)

Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
von: Yu, Sangwon, et al.
Veröffentlicht: (2024)

Controlled Text Generation for Black-box Language Models via Score-based Progressive Editor
von: Yu, Sangwon, et al.
Veröffentlicht: (2023)

DAFA: Distance-Aware Fair Adversarial Training
von: Lee, Hyungyu, et al.
Veröffentlicht: (2024)

Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents
von: Han, Hojae, et al.
Veröffentlicht: (2026)

Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models
von: Jung, Mingi, et al.
Veröffentlicht: (2025)

Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
von: Lee, Jonghyun, et al.
Veröffentlicht: (2024)

Contextualized Visual Personalization in Vision-Language Models
von: Oh, Yeongtak, et al.
Veröffentlicht: (2026)

Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models
von: Song, Jongyoon, et al.
Veröffentlicht: (2024)

On mitigating stability-plasticity dilemma in CLIP-guided image morphing via geodesic distillation loss
von: Oh, Yeongtak, et al.
Veröffentlicht: (2024)

Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation
von: Luo, Sichun, et al.
Veröffentlicht: (2025)

Making Long-Context Language Models Better Multi-Hop Reasoners
von: Li, Yanyang, et al.
Veröffentlicht: (2024)

Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
von: Park, Sangkwon, et al.
Veröffentlicht: (2026)

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
von: Yu, Zeping, et al.
Veröffentlicht: (2025)

EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
von: Lee, Che Hyun, et al.
Veröffentlicht: (2025)

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
von: Lee, Saehyung, et al.
Veröffentlicht: (2024)

DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections
von: Park, Jiwon, et al.
Veröffentlicht: (2025)

The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models
von: Lee, Taewhoo, et al.
Veröffentlicht: (2025)

NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts
von: Gupta, Abhay, et al.
Veröffentlicht: (2025)

Do Large Language Models Latently Perform Multi-Hop Reasoning?
von: Yang, Sohee, et al.
Veröffentlicht: (2024)

Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models
von: Kim, Heeseung, et al.
Veröffentlicht: (2025)

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
von: Wang, Shenzhi, et al.
Veröffentlicht: (2026)

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
von: Li, Zhaoyi, et al.
Veröffentlicht: (2026)

Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions
von: Lee, Dongwook, et al.
Veröffentlicht: (2026)

BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical Domain
von: Kim, Yunsoo, et al.
Veröffentlicht: (2025)

EconCausal: A Context-Aware Economic Reasoning Benchmark for Large Language Models
von: Lee, Donggyu, et al.
Veröffentlicht: (2025)

MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generation
von: Lee, Jungyeon, et al.
Veröffentlicht: (2025)

Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection
von: Lee, Saehyung, et al.
Veröffentlicht: (2024)

ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
von: Ma, Huipeng, et al.
Veröffentlicht: (2026)

RPM: Reasoning-Level Personalization for Black-Box Large Language Models
von: Kim, Jieyong, et al.
Veröffentlicht: (2025)

ETHIC: Evaluating Large Language Models on Long-Context Tasks with High Information Coverage
von: Lee, Taewhoo, et al.
Veröffentlicht: (2024)

FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning
von: Kim, Seunghee, et al.
Veröffentlicht: (2024)

DEBATE: Devil's Advocate-Based Assessment and Text Evaluation
von: Kim, Alex, et al.
Veröffentlicht: (2024)

CHOP: Chunkwise Context-Preserving Framework for RAG on Multi Documents
von: Park, Hyunseok, et al.
Veröffentlicht: (2026)