Image de couverture de livre

Don't Make the LLM Read the Graph: Make the Graph Think

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Yuqi, Meng, Tianqin, Liu, George, Panwar, Yashraj, Chaudhry, Lakshya, Ilham, Munasib, Chadha, Aman
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)
par: Lade, Ankit Hemant, et autres
Publié: (2026)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
par: Hassid, Michael, et autres
Publié: (2025)

Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
par: An, Sohyun, et autres
Publié: (2025)

Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
par: Lacombe, Romain, et autres
Publié: (2025)

Reasoning Models Don't Always Say What They Think
par: Chen, Yanda, et autres
Publié: (2025)

What LLMs Think When You Don't Tell Them What to Think About?
par: Kwon, Yongchan, et autres
Publié: (2026)

Don't Think of the White Bear: Ironic Negation in Transformer Models Under Cognitive Load
par: Mann, Logan, et autres
Publié: (2025)

Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
par: Liu, Runxuan, et autres
Publié: (2025)

Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries
par: Perez, Natalie, et autres
Publié: (2026)

Don't Forget to Connect! Improving RAG with Graph-based Reranking
par: Dong, Jialin, et autres
Publié: (2024)

Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
par: Wang, Haoyu, et autres
Publié: (2026)

Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making
par: Wan, Xu, et autres
Publié: (2025)

Don't Pay Attention
par: Hammoud, Mohammad, et autres
Publié: (2025)

Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
par: Li, Zeju, et autres
Publié: (2025)

Reasoning Models Reason Well, Until They Don't
par: Rameshkumar, Revanth, et autres
Publié: (2025)

Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context
par: Das, Nilanjana, et autres
Publié: (2024)

From Fog to Failure: The Unintended Consequences of Dehazing on Object Detection in Clear Images
par: Kumar, Ashutosh, et autres
Publié: (2025)

TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
par: Das, Amitava, et autres
Publié: (2025)

AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach
par: Amirizaniani, Maryam, et autres
Publié: (2024)

Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering
par: Chowdhury, Arijit Ghosh, et autres
Publié: (2023)

Can AI Assistants Know What They Don't Know?
par: Cheng, Qinyuan, et autres
Publié: (2024)

Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
par: Zhou, Jin Peng, et autres
Publié: (2024)

Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges
par: Samuel, Vinay, et autres
Publié: (2023)

DSADF: Thinking Fast and Slow for Decision Making
par: Dou, Zhihao, et autres
Publié: (2025)

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
par: Zhang, Jiefu, et autres
Publié: (2026)

Assessing LLM Reliability on Temporally Recent Open-Domain Questions
par: Krishnappa, Pushwitha, et autres
Publié: (2026)

Don't Blink: Evidence Collapse during Multimodal Reasoning
par: Raghu, Suresh, et autres
Publié: (2026)

Don't Get Too Excited -- Eliciting Emotions in LLMs
par: Fazzi, Gino Franco, et autres
Publié: (2025)

Don't Just Fine-tune the Agent, Tune the Environment
par: Lu, Siyuan, et autres
Publié: (2025)

Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Literal Extraction, Logical Inference, and Hallucination Risks in Long-Context LLMs
par: Ebrahimzadeh, Amirali, et autres
Publié: (2026)

Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
par: Sharma, Aman, et autres
Publié: (2025)

LLM Cyber Evaluations Don't Capture Real-World Risk
par: Lukošiūtė, Kamilė, et autres
Publié: (2025)

ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment
par: Wanaskar, Kapil, et autres
Publié: (2026)

Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target
par: Kim, Taesan, et autres
Publié: (2026)

Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks
par: Chochlakis, Georgios, et autres
Publié: (2024)

Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning
par: Gao, Hang, et autres
Publié: (2025)

Don't Kill the Baby: The Case for AI in Arbitration
par: Broyde, Michael, et autres
Publié: (2024)

Reverse Thinking Makes LLMs Stronger Reasoners
par: Chen, Justin Chih-Yao, et autres
Publié: (2024)

Implicit Intelligence -- Evaluating Agents on What Users Don't Say
par: Sirdeshmukh, Ved, et autres
Publié: (2026)

What We Don't C: Manifold Disentanglement for Structured Discovery
par: Rogers, Brian, et autres
Publié: (2025)