Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories
cs.LG, cs.AI, cs.IR
Submitted: 2026-09-01
Updated: 2026-09-01
Comments: 18 pages, 3 figures, code at https://github.com/nabirarashid/structural-retrieval
Code: https://github.com/nabirarashid/structural-retrieval
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
- A Benchmark for Procedural Memory Retrieval in Language Agents
- Passage Re-ranking with BERT
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Large Language Models Can Be Easily Distracted by Irrelevant Context
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks