Cover Image

Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bajaj, Anooshka, Mistry, Deven Mahesh, Maini, Sahaj Singh, Aggarwal, Yash, Tiganj, Zoran
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training
by: Mistry, Deven Mahesh, et al.
Published: (2025)

Temporal Dependencies in In-Context Learning: The Role of Induction Heads
by: Bajaj, Anooshka, et al.
Published: (2026)

Who Do LLMs Trust? Human Experts Matter More Than Other LLMs
by: Bajaj, Anooshka, et al.
Published: (2026)

High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination
by: Maini, Sahaj Singh, et al.
Published: (2026)

Gradual Forgetting: Logarithmic Compression for Extending Transformer Context Windows
by: Dickson, Billy, et al.
Published: (2025)

Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
by: Kabir, Md Rysul, et al.
Published: (2026)

Vision-language models learn the geometry of human perceptual space
by: Sanders, Craig, et al.
Published: (2025)

REAMS: Reasoning Enhanced Algorithm for Maths Solving
by: Singh, Eishkaran, et al.
Published: (2025)

Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO
by: Pappone, Francesco, et al.
Published: (2025)

Understanding In-Context Learning Beyond Transformers: An Investigation of State Space and Hybrid Architectures
by: Wang, Shenran, et al.
Published: (2025)

Deep reinforcement learning with time-scale invariant memory
by: Kabir, Md Rysul, et al.
Published: (2024)

DateLogicQA: Benchmarking Temporal Biases in Large Language Models
by: Bhatia, Gagan, et al.
Published: (2024)

Neurosymbolic Retrievers for Retrieval-augmented Generation
by: Saxena, Yash, et al.
Published: (2026)

Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
by: Rajesh, Shreyas, et al.
Published: (2025)

Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models
by: Das, Rocktim Jyoti, et al.
Published: (2023)

Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC)
by: Wang, Peidong
Published: (2026)

Unveiling Divergent Inductive Biases of LLMs on Temporal Data
by: Kishore, Sindhu, et al.
Published: (2024)

State Design Matters: How Representations Shape Dynamic Reasoning in Large Language Models
by: Wong, Annie, et al.
Published: (2026)

One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models
by: Fein, Daniel, et al.
Published: (2026)

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
by: Aggarwal, Pranjal, et al.
Published: (2025)

Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study
by: Bouchard, Dylan, et al.
Published: (2026)

From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
by: Li, Lehui, et al.
Published: (2026)

How Small Transformation Expose the Weakness of Semantic Similarity Measures
by: Nikiema, Serge Lionel, et al.
Published: (2025)

Mitigating Social Biases in Language Models through Unlearning
by: Dige, Omkar, et al.
Published: (2024)

RexBERT: Context Specialized Bidirectional Encoders for E-commerce
by: Bajaj, Rahul, et al.
Published: (2026)

Mining Beyond the Bools: Learning Data Transformations and Temporal Specifications
by: Kouteili, Sam Nicholas, et al.
Published: (2026)

Neural Retrievers are Biased Towards LLM-Generated Content
by: Dai, Sunhao, et al.
Published: (2023)

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
by: Adarsh, Shivam, et al.
Published: (2026)

Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations
by: Bochkov, A.
Published: (2025)

Transformer-based Joint Modelling for Automatic Essay Scoring and Off-Topic Detection
by: Das, Sourya Dipta, et al.
Published: (2024)

NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness
by: Singhal, Manav, et al.
Published: (2024)

TransXSSM: A Hybrid Transformer State Space Model with Unified Rotary Position Embedding
by: Wu, Bingheng, et al.
Published: (2025)

Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators
by: Bansal, Hritik, et al.
Published: (2025)

Do Biased Models Have Biased Thoughts?
by: Rajwal, Swati, et al.
Published: (2025)

Repeat After Me: Transformers are Better than State Space Models at Copying
by: Jelassi, Samy, et al.
Published: (2024)

Comparative Analysis of Efficient Adapter-Based Fine-Tuning of State-of-the-Art Transformer Models
by: Siddiqui, Saad Mashkoor, et al.
Published: (2025)

Automated Extraction and Creation of FBS Design Reasoning Knowledge Graphs from Structured Data in Product Catalogues Lacking Contextual Information
by: Sahadevan, Vijayalaxmi, et al.
Published: (2024)

Semantic Tokens in Retrieval Augmented Generation
by: Suro, Joel
Published: (2024)

How do Transformer Embeddings Represent Compositions? A Functional Analysis
by: Nagar, Aishik, et al.
Published: (2025)

Revisiting the Shape Convention of Transformer Language Models
by: Liao, Feng-Ting, et al.
Published: (2026)