Cover Image

Disentangling Recall and Reasoning in Transformer Models through Layer-wise Attention and Activation Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fartale, Harshwardhan, Kattamuri, Ashish, Raja, Rahul, Vats, Arpita, Prasad, Ishita, Moharir, Akshata Kishore
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Equilibrium Dynamics and Mitigation of Gender Bias in Synthetically Generated Data
by: Kattamuri, Ashish, et al.
Published: (2025)

RADAR: Mechanistic Pathways for Detecting Data Contamination in LLM Evaluation
by: Kattamuri, Ashish, et al.
Published: (2025)

Bridging the Semantic Gap: Contrastive Rewards for Multilingual Text-to-SQL with GRPO
by: Kattamuri, Ashish, et al.
Published: (2025)

Evaluating Generalization and Representation Stability in Small LMs via Prompting, Fine-Tuning and Out-of-Distribution Prompts
by: Raja, Rahul, et al.
Published: (2025)

A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
by: Raja, Rahul, et al.
Published: (2025)

The Nonverbal Gap: Toward Affective Computer Vision for Safer and More Equitable Online Dating
by: Kandala, Ratna, et al.
Published: (2026)

"What if she doesn't feel the same?" What Happens When We Ask AI for Relationship Advice
by: Manchanda, Niva, et al.
Published: (2025)

Multimedia-Aware Question Answering: A Review of Retrieval and Cross-Modal Reasoning Architectures
by: Raja, Rahul, et al.
Published: (2025)

EchoGuard: An Agentic Framework with Knowledge-Graph Memory for Detecting Manipulative Communication in Longitudinal Dialogue
by: Kandala, Ratna, et al.
Published: (2026)

Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
by: Vats, Arpita, et al.
Published: (2024)

FUSE : A Ridge and Random Forest-Based Metric for Evaluating MT in Indigenous Languages
by: Raja, Rahul, et al.
Published: (2025)

Beyond Nearest Neighbors: Semantic Compression and Graph-Augmented Retrieval for Enhanced Vector Search
by: Raja, Rahul, et al.
Published: (2025)

Counterfactual Risk Minimization with IPS-Weighted BPR and Self-Normalized Evaluation in Recommender Systems
by: Raja, Rahul, et al.
Published: (2025)

Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Review
by: Raja, Rahul, et al.
Published: (2025)

Multilingual State Space Models for Structured Question Answering in Indic Languages
by: Vats, Arpita, et al.
Published: (2025)

Designing Explainable Conversational Agentic Systems for Guaraní Speakers
by: Adorno, Samantha, et al.
Published: (2026)

Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?
by: Ramasethu, Aishwarya, et al.
Published: (2026)

From Explainability to Action: A Generative Operational Framework for Integrating XAI in Clinical Mental Health Screening
by: Kandala, Ratna, et al.
Published: (2025)

Towards Green AI: Energy-Efficient Training and Inference of Large Language Models
by: Vats, Harshwardhan, et al.
Published: (2025)

Cross-Lingual Mental Health Ontologies for Indian Languages: Bridging Patient Expression and Clinical Understanding through Explainable AI and Human-in-the-Loop Validation
by: Kandala, Ananth, et al.
Published: (2025)

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations
by: Borah, Abhilekh, et al.
Published: (2025)

Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting
by: Kumar, Raja, et al.
Published: (2024)

How Vision Becomes Language: A Layer-wise Information-Theoretic Analysis of Multimodal Reasoning
by: Wu, Hongxuan, et al.
Published: (2026)

Time Series Viewmakers for Robust Disruption Prediction
by: Chayapathy, Dhruva, et al.
Published: (2024)

From Recall to Reasoning: Automated Question Generation for Deeper Math Learning through Large Language Models
by: Yu, Yongan, et al.
Published: (2025)

A Layer-wise Analysis of Supervised Fine-Tuning
by: Zhao, Qinghua, et al.
Published: (2026)

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
by: Li, Ming, et al.
Published: (2025)

Disentangling Reasoning and Knowledge in Medical Large Language Models
by: Thapa, Rahul, et al.
Published: (2025)

Efficient Knowledge Deletion from Trained Models through Layer-wise Partial Machine Unlearning
by: Gogineni, Vinay Chakravarthi, et al.
Published: (2024)

LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
by: Kapadia, Shashank, et al.
Published: (2026)

Layer-wise Regularized Dropout for Neural Language Models
by: Ni, Shiwen, et al.
Published: (2024)

Uncertainty-Aware Regularization for Image-to-Image Translation
by: Vats, Anuja, et al.
Published: (2024)

Explainable AI: Comparative Analysis of Normal and Dilated ResNet Models for Fundus Disease Classification
by: Karthikayan, P. N., et al.
Published: (2024)

SlimGPT: Layer-wise Structured Pruning for Large Language Models
by: Ling, Gui, et al.
Published: (2024)

Layer-wise Positional Bias in Short-Context Language Modeling
by: Rahimi, Maryam, et al.
Published: (2026)

Observation-Free Attacks on Online Learning to Rank
by: Chattopadhyay, Sameep, et al.
Published: (2025)

LATTE: Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer
by: Wang, Jiing-Ping, et al.
Published: (2024)

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
by: Yun, Taewon, et al.
Published: (2026)

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
by: Lv, Ang, et al.
Published: (2024)

Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction
by: Li, Guozheng, et al.
Published: (2024)