Davood Rafiei — Publications by Research Area

Streaming Data Management

  1. Approximately detecting duplicates for streaming data using stable bloom filters. SIGMOD 2006.
  2. New estimation algorithms for streaming data: Count-min can do more. 2007.
  3. Top-k frequent term queries on streaming data. ICDE 2019.
  4. Similarity join and similarity self-join size estimation in a streaming environment. TKDE 2019.

Web Search and Question Answering

    Web Search and Information Retrieval

    1. What is this page known for? Computing web page reputations. WWW 2000.
    2. What do the neighbours think? Computing Web page reputations. IEEE Data Engineering Bulletin 2000.
    3. An autonomous page ranking method for metasearch engines. WWW 2002.
    4. Focused co-citation: Improving the retrieval of related pages on the web. WWW 2004.
    5. ALVIN: a system for visualizing large networks. WWW 2005.
    6. Bulk loading large collections of hyperlinked resources. Hypertext and Hypermedia 2005.
    7. Dewild: a tool for searching the web using wild cards. SIGIR 2006.
    8. Data extraction from the web using wild card queries. CIKM 2009.
    9. Diversifying web search results. WWW 2010.
    10. Answer typing for information retrieval. CIKM 2009.
    11. Index structures for efficiently searching natural language text. CIKM 2010.

    Question Answering

    1. Flexible answer typing with discriminative preference ranking. EACL 2009.
    2. Detecting frozen phrases in open-domain question answering. SIGIR 2022.
    3. Limitations of open-domain question answering benchmarks for document-level reasoning. SIGIR 2023.
    4. Evaluating open-domain question answering in the era of large language models. ACL 2023.
    5. LongRecall: A structured approach for robust recall evaluation in long-form text. arXiv 2025.
    6. Prism: Agentic retrieval with llms for multi-hop question answering. arXiv 2025.
    7. Do nugget-based evaluation patterns generalize to list-QA?. GEM @ ACL 2026.

Natural Language Data Access

  1. Natural language data management and interfaces. Morgan & Claypool Book, 2018.
  2. Natural language interfaces to databases. Springer Book, 2024.
  3. DIN-SQL: Decomposed in-context learning of text-to-SQL with self-correction. NeurIPS 2023.
  4. Evaluating cross-domain text-to-SQL models and benchmarks. EMNLP 2023.
  5. DTS-SQL: Decomposed text-to-sql with small large language models. EMNLP 2024.
  6. SQL-Encoder: Improving NL2SQL in-context learning through a context-aware encoder. arXiv 2024.
  7. Do LLMs align with my task? Evaluating text-to-SQL via dataset alignment. arXiv 2025.
  8. Rethinking schema linking: A context-aware bidirectional retrieval approach for text-to-sql. EACL 2026.
  9. Confidence estimation for text-to-sql in large language models. AAAI 2026.
  10. How far can they map? Probing llm capabilities for cross-schema sql generation. Beyond SQL @ ICDE 2026.
  11. SQL-exchange: Transforming SQL queries across domains. VLDB 2026.
  12. Text-to-SQL evaluation toolkit. VLDB 2026.
  13. FlexSQL: Flexible exploration and execution make better text-to-SQL agents. arXiv 2026.
  14. SynSQL: Synthesizing relational databases for robust evaluation of text-to-SQL systems. arXiv 2026.

Structured Data Understanding and Integration

    Semantic Understanding of Structured Data

    1. SAND: semantic annotation of numeric data in web tables. CIKM 2023.
    2. Improving Column Type Annotation Using Large Language Models. TaDA @ VLDB 2023.
    3. TabSQLify: Enhancing reasoning capabilities of LLMs through table decomposition. NAACL 2024.
    4. NormTab: Improving symbolic reasoning in LLMs through tabular data normalization. EMNLP 2024.
    5. Evaluating Column Type Annotation Models and Benchmarks. WWW 2025.
    6. MixedSAND: Semantic Annotation of Mixed-unit Numeric Data. WWW 2025.
    7. eC-Tab2Text: Aspect-based text generation from e-commerce product tables. NAACL 2025.

    Data Integration, Transformation, and Preparation

    1. Efficiently transforming tables for joinability. ICDE 2022.
    2. BareTQL: An interactive system for searching and extraction of open data tables. IUI 2022.
    3. Table union search with preferences. TaDA@VLDB 2023.
    4. Interactive set discovery. EDBT 2023.
    5. DTT: An example-driven tabular transformer for joinability by leveraging large language models. SIGMOD 2024.
    6. TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations. VLDB 2024.
    7. GXJoin: Generalized cell transformations for explainable joinability. ADBIS 2024.
    8. WebTableX: Efficiently discovering web table transformations through sampling. CIKM 2025.
    9. LDI: Localized data imputation for text-rich tables. TaDA@VLDB 2026.

    Entity Resolution and Disambiguation

    1. Geotagging named entities in news and online documents. CIKM 2016.
    2. A coherent unsupervised model for toponym resolution. WWW 2018.
    3. Strategies for geographical scoping and improving a gazetteer. WWW 2018.
    4. Location-aware named entity disambiguation. CIKM 2021.
    5. Probing the robustness of pre-trained language models for entity matching. CIKM 2022.
    6. Product entity matching via tabular data. CIKM 2023.

Language Models and Applications

  1. KidLM: Advancing language models for children–early insights and future directions. EMNLP 2024, Best Resource Paper Award.
  2. SurveyGen: Quality-aware scientific survey generation with large language models. EMNLP 2025.
  3. OpinioRAG: Towards generating user-centric opinion highlights from large-scale online reviews . COLM 2025.
  4. Which english do LLMs prefer? Triangulating structural bias towards american English in foundation models . arXiv 2026.

Database Systems

  1. Bulk loading a linear hash file. DaWAK 2006.
  2. Efficient indexing and querying over syntactically annotated trees. VLDB 2012.

Data Mining and Network Analysis

  1. Effectively visualizing large networks through sampling. IEEE Visualization 2005.
  2. Leveraging editor collaboration patterns in Wikipedia. Hypertext and Hypermedia 2012.
  3. Predicting political preference of Twitter users. SNAM 2013.
  4. Finding surprisingly frequent patterns of variable lengths in sequence data. SDM 2016.
  5. Tracking User Activities and Marketplace Dynamics in Classified Ads. WI 2016.
  6. Characterizing users in an online classified ad network. Web Intelligence 2016.
  7. On the role of reviewer expertise in temporal review helpfulness prediction. EACL 2023.
  8. Adversarial botometer: adversarial analysis for social bot detection. SNAM 2024.