mlsanityData to 14 Oct 2026

ConceptCarve: Dynamic Realization of Evidence

arXiv 2504.07228 ↗First posted 9 Apr 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Finding evidence for human opinion and behavior at scale is a challenging task, often requiring an understanding of sophisticated thought patterns among vast online communities found on social media. For example, studying how gun ownership is related to the perception of Freedom, requires a retrieval system that can operate at scale over social media posts, while dealing with two key challenges: (1) identifying abstract concept instances, (2) which can be instantiated differently across different communities. To address these, we introduce ConceptCarve, an evidence retrieval framework that utilizes traditional retrievers and LLMs to dynamically characterize the search space during retrieval. Our experiments show that ConceptCarve surpasses traditional retrieval systems in finding evidence within a social media community. It also produces an interpretable representation of the evidence for that community, which we use to qualitatively analyze complex thought patterns that manifest differently across the communities.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 63 references that are in the map. First posted on arXiv 9 Apr 2025.

Builds on

36 of 63 references.

References · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  6. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  7. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  8. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  9. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 801
  10. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  11. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  12. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 272
24 more
  1. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 235
  2. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  3. 2024Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooMcited by 78
  4. 2020ConvoKit: A Toolkit for the Analysis of Conversationscited by 72
  5. 2023Goal Driven Discovery of Distributional Differences via Language Descriptionscited by 62
  6. 2023Goal-Driven Explainable Clustering via Language Descriptionscited by 58
  7. 2021Semantic Models for the First-stage Retrieval: A Comprehensive Reviewcited by 57
  8. 2020BERT-QE: Contextualized Query Expansion for Document Re-rankingcited by 40
  9. 2024Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Modelscited by 40
  10. 2023UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankerscited by 37
  11. 2021Pseudo-Relevance Feedback for Multiple Representation Dense Retrievalcited by 32
  12. 2023Large Language Models are Strong Zero-Shot Retrievercited by 26
  13. 2023When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasetscited by 26
  14. 2023MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansioncited by 23
  15. 2024Who's Who: Large Language Models Meet Knowledge Conflicts in Practicecited by 21
  16. 2023Natural Language Decompositions of Implicit Content Enable Better Text Representationscited by 19
  17. 2024Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensionscited by 16
  18. 2023Interactive Concept Learning for Uncovering Latent Themes in Large Text Collectionscited by 15
  19. 2023Search-Adaptor: Embedding Customization for Information Retrievalcited by 11
  20. 2020Understanding Politics via Contextualized Discourse Processingcited by 9
  21. 2023Description-Based Text Similaritycited by 7
  22. 2022Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrievalcited by 4
  23. 2023"A Tale of Two Movements": Identifying and Comparing Perspectives in #BlackLivesMatter and #BlueLivesMatter Movements-related Tweets using Weakly Supervised Graph-based Structured Predictioncited by 4
  24. 2023Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrievalcited by 4

Built on by

Not cited yet.