Document retrieval identifies relevant documents but does not provide fine-grained evidence cues, such as specific relevant spans. A possible solution is to apply an LLM after retrieval; however, this introduces significant computational overhead and limits practical deployment. We propose FGR-ColBERT, a modification of ColBERT retrieval model that integrates fine-grained relevance signals distilled from an LLM directly into the retrieval function. Experiments on MS MARCO show that FGR-ColBERT (110M) achieves a token-level F1 of 64.5, exceeding the 62.8 of Gemma 2 (27B), despite being approximately 245 times smaller. At the same time, it preserves retrieval effectiveness (99% relative Recall@50) and remains efficient, incurring only a ~1.12x latency overhead compared to the original ColBERT.
Figures & tables
Figure 1: (a) ColBERT retrieval followed by LLM span extraction vs. our approach with integrated LLM knowledge transfer. (b) Newly proposed late interaction with an added token-level relevance scoring, preserving document-level relevance.
Table 2
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
Computation Step
Expression
FLOPs
Up-Scaling
A=EdR⋅W1
2nhh2
Element-wise ReLU
A′=ReLU(A)
nh2
Down-Scaling
B=A′⋅W2
2nhh2
Residual Connection
EdI=EdR+B
nh
Total FLOPs
4nhh2+nh2+nh
Appendix
Table 3: FLOP breakdown for the FFN network transforming embeddings for fine-grained relevance extraction.
Figure 2: Three positive passage-query pairs and corresponding token-level scores (highlighted; darker is higher) derived from the FGR-ColBERT model and fine-grained relevance cues provided by Gemma 2 (bold).
Multi-vector dense retrieval models, such as ColBERT, achieve strong retrieval effectiveness by modelling fine-grained token-level interactions between queries and documents. Methods such as PLAID use centroid-based quantisation of each token's vector to reduce the index size and speed up retrieval while maintaining strong effectiveness. In this work, we introduce PLAID-PRF, a method that performs Pseudo-Relevance Feedback (PRF) over PLAID to reformulate ColBERT's query vectors based on the top-retrieved results. In contrast with prior methods that perform PRF on multi-vector retrieval models, PLAID-PRF keeps computational costs low by leveraging the internal PLAID centroid vectors, treating them similarly to tokens in traditional PRF methods. The method selects a small and diverse set of high-utility expansion vectors and appends them to the original query, rerunning PLAID to refine both candidate generation and final scoring. Extensive experiments on the standard in-domain MSMARCO and four out-of-domain BEIR benchmarks show that PLAID-PRF consistently improves retrieval effectiveness over various baselines. In particular, PLAID-PRF improves over PLAID by up to 4.3% nDCG@10 and 7.3% MRR@10, while introducing substantially less computation overhead than prior PRF methods. The results demonstrate that our proposed centroid-aware PRF method offers an effective and lightweight mechanism to improve the quality of top-ranked retrieved results. Overall, this work enables effective and efficient feedback-aware late-interaction retrieval without expensive query-time document-token clustering.
Xiao Wang, Sean MacAvaney, Craig Macdonald
University of International Business and Economics Beijing, China · University of Glasgow Glasgow, United Kingdom
Multi-vector retrieval models such as ColBERT often outperform single-vector models of comparable scale by matching queries and documents at the token level. However, retaining a vector for every token substantially increases storage requirements and slows retrieval compared to single-vector bi-encoders, limiting their scalability. We introduce FLINT (Fixed-budget Late INTeraction), an architecture that uses attention-based pooling to represent each query and document with a fixed number of embedding vectors. Unlike architectures that pool only document representations while retaining token-level queries, FLINT applies pooling symmetrically to both sides, limiting document storage and the number of vector comparisons needed during retrieval. FLINT achieves comparable ranking effectiveness to the closest baselines on BEIR and outperforms them on several benchmarks with longer and more complex queries, including BrowseComp+, CRUMB, and TREC Tip-of-the-Tongue 2025. We demonstrate that FLINT's effectiveness-efficiency benefits extend across encoder architectures, testing it on two separate backbones (BERT and ModernBERT). On long-query corpora, FLINT delivers 1.5-2.8 times faster end-to-end retrieval than ConstBERT, the closest baseline. FLINT also reduces index size by 5.3-9.3 times relative to token-level late-interaction models such as ColBERTv2.
Himank Handa, Negar Arabzadeh, Matei Zaharia
University of Illinois Urbana-Champaign · University of California, Berkeley
Language models (LMs) raise an intriguing alternative to vector-based retrieval: conditioning on an in-context corpus and directly generating a relevant answer. However, prior work has largely focused on proprietary systems or the smaller-scale reranking task, leaving corpus-scale in-context retrieval largely unexplored. In this work, we present the first systematic study of in-context retrieval on two scales practical retrievers demand: million-token corpora and length-generalization far beyond training-time sizes. We first introduce BlockSearch, a 0.6B LM retriever whose architectural and training modifications improve over prior LM baselines and length-generalize up to 10 times beyond its training regime. Nevertheless, retrieval still collapses under more extreme extrapolation. We trace this failure to an attention dilution effect: as the corpus grows, irrelevant documents dominate the softmax denominator, reducing the normalized mass on the gold document even when its pre-softmax score stays high. Motivated by this analysis, we introduce length-aware adjustments to the attention softmax and document-level sparse attention. With these modifications, at the million-token scale, our model matches dense retrieval on widely studied benchmarks (e.g, MS MARCO and NQ), while outperforming the concurrent model MSA despite being 7 times smaller. Furthermore, it significantly outperforms dense retrieval on tasks requiring entirely different notions of similarity, such as LIMIT, achieving a 3 times higher score. Together, our results position in-context retrieval a promising alternative to classical retrieval while emphasizing attention control under extreme context growth as a new challenge.