# How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset

arXiv: https://arxiv.org/abs/2105.07975 · HTML: https://mlsanity.com/paper/2105.07975/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2021.

## Built on by (most cited first, 18 of 18)

- [Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback](https://mlsanity.com/paper/2108.13454/) (2021)
- [CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos](https://mlsanity.com/paper/2204.00716/) (2022)
- [AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking](https://mlsanity.com/paper/2505.18512/) (2025)
- [Hypencoder: Hypernetworks for Information Retrieval](https://mlsanity.com/paper/2502.05364/) (2025)
- [A Reproducibility Study of LLM-Based Query Reformulation](https://mlsanity.com/paper/2604.27421/) (2026)
- [LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback](https://mlsanity.com/paper/2204.11545/) (2022)
- [Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systems](https://mlsanity.com/paper/2206.12993/) (2022)
- [Query-Specific Knowledge Graphs for Complex Finance Topics](https://mlsanity.com/paper/2211.04142/) (2022)
- [Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding](https://mlsanity.com/paper/2301.03765/) (2023)
- [Exploring the Effectiveness of Multi-stage Fine-tuning for Cross-encoder Re-rankers](https://mlsanity.com/paper/2503.22672/) (2025)
- [ReFormeR: Learning and Applying Explicit Query Reformulation Patterns](https://mlsanity.com/paper/2604.01417/) (2026)
- [ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback](https://mlsanity.com/paper/2606.13905/) (2026)
- [The Surprising Effectiveness of Rankers Trained on Expanded Queries](https://mlsanity.com/paper/2404.02587/) (2024)
- [Understanding the User: An Intent-Based Ranking Dataset](https://mlsanity.com/paper/2408.17103/) (2024)
- [BlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs](https://mlsanity.com/paper/2602.05448/) (2026)
- [Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval](https://mlsanity.com/paper/2604.27037/) (2026)
- [PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID](https://mlsanity.com/paper/2607.18626/) (2026)
- [Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval](https://mlsanity.com/paper/2609.05110/) (2026)

## Abstract (arXiv)

Deep Learning Hard (DL-HARD) is a new annotated dataset designed to more effectively evaluate neural ranking models on complex topics. It builds on TREC Deep Learning (DL) topics by extensively annotating them with question intent categories, answer types, wikified entities, topic categories, and result type metadata from a commercial web search engine. Based on this data, we introduce a framework for identifying challenging queries. DL-HARD contains fifty topics from the official DL 2019/2020 evaluation benchmark, half of which are newly and independently assessed. We perform experiments using the official submitted runs to DL on DL-HARD and find substantial differences in metrics and the ranking of participating systems. Overall, DL-HARD is a new resource that promotes research on neural ranking methods by focusing on challenging and complex topics.