Cover Image

Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Yang, Zhang, Yifan, Wang, Yiwei, Cai, Yujun, Wu, Yurong, Wang, Yuran, Xu, Ning, Cheng, Jian
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation
by: Wu, Yang, et al.
Published: (2025)

Symbolic or Numerical? Understanding Physics Problem Solving in Reasoning LLMs
by: Dan, Nifu, et al.
Published: (2025)

Are LLMs Really Not Knowledgeable? Mining the Submerged Knowledge in LLMs' Memory
by: Tao, Xingjian, et al.
Published: (2024)

Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM
by: Xiong, Zhen, et al.
Published: (2025)

ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning
by: Tao, Xingjian, et al.
Published: (2026)

Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding
by: Wang, Cheng, et al.
Published: (2024)

From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs
by: Li, Guocong, et al.
Published: (2025)

SemVink: Advancing VLMs' Semantic Understanding of Optical Illusions via Visual Global Thinking
by: Li, Sifan, et al.
Published: (2025)

Finding Distributed Object-Centric Properties in Self-Supervised Transformers
by: Rawlekar, Samyak, et al.
Published: (2026)

Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
by: Sheshanarayana, Disha, et al.
Published: (2026)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
by: Li, Li, et al.
Published: (2025)

Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models
by: Xiong, Zhen, et al.
Published: (2025)

Structured Attention Matters to Multimodal LLMs in Document Understanding
by: Liu, Chang, et al.
Published: (2025)

See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses
by: Chen, Yulong, et al.
Published: (2024)

Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding
by: Sun, Bowen, et al.
Published: (2025)

PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
by: Wu, Yuhe, et al.
Published: (2026)

A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement
by: Li, Yuran, et al.
Published: (2026)

Unveiling the Potential of Diffusion Large Language Model in Controllable Generation
by: Xiong, Zhen, et al.
Published: (2025)

GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation
by: Li, Sifan, et al.
Published: (2026)

Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs
by: Luo, Yi, et al.
Published: (2025)

Understanding GUI Agent Localization Biases through Logit Sharpness
by: Tao, Xingjian, et al.
Published: (2025)

Vulnerability of LLMs to Vertically Aligned Text Manipulations
by: Li, Zhecheng, et al.
Published: (2024)

Structured Outputs Enable General-Purpose LLMs to be Medical Experts
by: Guo, Guangfu, et al.
Published: (2025)

The Potential of LLMs in Medical Education: Generating Questions and Answers for Qualification Exams
by: Zhu, Yunqi, et al.
Published: (2024)

Ask, Answer, and Detect: Role-Playing LLMs for Personality Detection with Question-Conditioned Mixture-of-Experts
by: Lyu, Yifan, et al.
Published: (2025)

ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinations
by: Wu, Yike, et al.
Published: (2025)

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction
by: Zhang, Chen, et al.
Published: (2026)

$A^2R^2$: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement
by: Li, Zhecheng, et al.
Published: (2025)

LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
by: Dai, Yifan, et al.
Published: (2026)

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
by: Zhang, Huanyu, et al.
Published: (2025)

MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks
by: You, Wenhao, et al.
Published: (2025)

Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs
by: Li, Sifan, et al.
Published: (2025)

Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasoning
by: Zhu, Jiayuan, et al.
Published: (2025)

Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning
by: Hao, Zhuoyuan, et al.
Published: (2026)

AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models
by: Shen, Zhanyu, et al.
Published: (2026)

A Survey on Latent Reasoning
by: Zhu, Rui-Jie, et al.
Published: (2025)

Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach
by: Wu, Yurong, et al.
Published: (2025)

Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs
by: Wang, Kai, et al.
Published: (2026)

Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation
by: Zhang, Yong, et al.
Published: (2025)

Self-Manager: Parallel Agent Loop for Long-form Deep Research
by: Xu, Yilong, et al.
Published: (2026)