Papers with ColBERT
ABNIRML: Analyzing the Behavior of Neural IR Models (2022.tacl-1)
Copied to clipboard
| Challenge: | Pretrained contextualized language models such as BERT and T5 have established a new state-of-the-art for ad-hoc ranking. |
| Approach: | They propose a framework for Analyzing the Behavior of Neural IR ModeLs that includes new types of diagnostic probes that allow us to test several characteristics that are not addressed by previous techniques. |
| Outcome: | The proposed framework tests writing styles, factuality, sensitivity to paraphrasing and word order, and can be used to identify unintended biases. |
An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage Matching (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing models that learn semantic representations of passages are prone to performance degradation . embedding binarization is a promising branch of model compression . |
| Approach: | They propose an embedding binarization approach that can be used to optimize for online inference. |
| Outcome: | The proposed model can perform query-passage matching acceleration. |
NEAT-IR: Neural Explainable Analysis Tool for Information Retrieval (2026.acl-srw)
Copied to clipboard
| Challenge: | Neural IR models achieve strong performance but remain difficult to interpret. |
| Approach: | They propose a black-box analysis framework that explains ColBERT’s ranking behavior using 26 classical IR features. |
| Outcome: | The proposed framework preserves ColBERT’s rankings nearly perfectly, yet only explain R2 0.28 of score variance. |
XTR meets ColBERTv2: Adding ColBERTv2 Optimizations to XTR (2025.coling-industry)
Copied to clipboard
| Challenge: | XTR eliminates the need for multi-stage retrieval, but doesn't incorporate efficiency optimizations from ColBERTv2 which improve indexing and retrieval speed. |
| Approach: | They propose a multi-vector retrieval method that simplifies retrieval into a single stage through a modified learning objective. |
| Outcome: | The proposed method eliminates the need for multistage retrieval but doesn't incorporate efficiency optimizations from ColBERTv2 which improve indexing and retrieval speed. |
UR2N: Unified Retriever and ReraNker (2025.coling-industry)
Copied to clipboard
| Challenge: | XTR-style retrieval on top of trained Mono-T5 reranker is suboptimal for two-stage retrieval, arguing that it is sub-optimal. |
| Approach: | They propose a unified encoder-decoder architecture with a novel training regimen which enables the encoder representation to be used for retrieval and the decoder for re-ranking within a single unified model. |
| Outcome: | The proposed architecture outperforms ColBERT, XTR, and even serves as a superior reranker compared to the Mono-T5 re-ranker. |
Relevance-guided Supervision for OpenQA with ColBERT (2021.tacl-1)
Copied to clipboard
| Challenge: | Recent work has focused on learning to retrieve passages for open-domain question answering . if notions of relevance are not tailored to questions, the MRC model will not reliably see the best passages . |
| Approach: | They propose a retrieval model that uses coarse-grained vector representations of questions and passages to adapt it to OpenQA. |
| Outcome: | The proposed system improves OpenQA retrieval on Natural Questions, SQuAD, and TriviaQA. |
Angel: Enterprise Search System for the Non-Profit Industry (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Non-profit industry needs a system for accurately matching fund-seekers with fund-givers aligned in cause and target beneficiary group. |
| Approach: | They propose a search system that takes a fund-giver’s mission description as input and returns a ranked list of fund-seekers as output. |
| Outcome: | The proposed system improves on the non-profit evaluation dataset and the state-of-the-art model. |
ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to improve retrieval effectiveness in high-resource languages are limited due to the lack of high-quality labeled data in non-English languages. |
| Approach: | They propose a modular dense retrieval model that learns from the rich data of a single high-resource language and effectively zero-shot transfers to a wide array of languages. |
| Outcome: | The proposed model performs well against state-of-the-art multilingual retrieval models trained on more extensive datasets in various languages. |
HIL: Hybrid Isotropy Learning for Zero-shot Performance in Dense retrieval (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in dense retrieval models have brought ColBERT to prominence in information retrieval, but it is underperforming in zero-shot tasks. |
| Approach: | They propose a Hybrid Isotropy Learning architecture that integrates isotropic and anisotropic representations to improve zero-shot retrieval performance. |
| Outcome: | The proposed model outperforms the baseline ColBERT model in BEIR benchmarks. |
Effective Contrastive Weighting for Dense Query Expansion (2023.acl-long)
Copied to clipboard
| Challenge: | Verbatim queries that do not adequately express the user's search intent are often lexical inadequacies. |
| Approach: | They propose a contrastive weighting model that learns to select the most useful expansion embeddings for semantic search. |
| Outcome: | The proposed model outperforms existing methods while maintaining its efficiency. |
Problem-Oriented Segmentation and Retrieval: Case Study on Tutoring Conversations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | POSR is a task of breaking down conversations into segments and linking each segment to the relevant reference item. |
| Approach: | They propose a task that breaks down conversations into segments and links each segment to the relevant reference item. |
| Outcome: | The proposed method outperforms independent segmentation pipelines and large language models on joint metrics. |
Pseudo-Relevance for Enhancing Document Representation (2022.emnlp-main)
Copied to clipboard
| Challenge: | a novel approach to document retrieval can be used to encode documents as vectors . a few query-relevant terms can be pruned out to reduce index overhead . |
| Approach: | They propose to enhance the document representation for the bi-encoder approach in dense document retrieval. |
| Outcome: | The proposed solution reduces latency and memory footprint up to 8- and 3-fold . it is validated on MSMARCO and real-world search query logs . |
Investigating Multi-layer Representations for Dense Passage Retrieval (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Dense retrieval models adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model contain different kinds of linguistic knowledge and behave differently during fine-tuning. |
| Approach: | They propose to utilize representations from multiple encoder layers to make up the representation of a document, which they denote Multi-layer Representations (MLR). |
| Outcome: | The proposed model outperforms dual encoder, ME-BERT and ColBERT in the single-vector retrieval setting and with other advanced training techniques. |
Leveraging Cognitive Complexity of Texts for Contextualization in Dense Retrieval (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to estimate semantic similarity of queries and documents rely on token-level information derived from query/document interactions. |
| Approach: | They propose a new DRM that leverages query/document interactions based on full embedding representations generated by a Transformer-based model. |
| Outcome: | The proposed model outperforms fine-tuning techniques on lightweight bi-encoders and traditional late-interaction models. |
A Counterfactual Explanation Framework for Retrieval Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing literature on explainability of information retrieval has focused on illustrating the concept of relevance concerning a retrieval model. |
| Approach: | They propose to add terms to a document to improve its ranking to answer the question of which words played a role in not being favored by a retrieval model. |
| Outcome: | The proposed framework predicts counterfactuals for statistical and deep-learning models. |