cs.IRNov 16, 2026

When the Bill Falls: Reusing the Old Index Defers,Never Avoids, Re-encoding in Complete Embedding-Model Migration

Authors: Nannan Zhao, Jiameng Zhang, Taoyu Zhong, Hao Wang, Bo Wang

Organizations: Northwestern Polytechnical University Xi’an, China

Abstract

Upgrading the embedding model behind a vector index requires re-encoding the corpus. Recent work reuses the old index through adapters or window re-ranking. Across sixteen model pairs on passage and code corpora, plus eleven on Natural Questions (NQ), we find three results. First, reuse never avoids re-encoding: if migration must complete, every strategy eventually encodes every document; reuse only changes when that work is paid and the quality served meanwhile. Second, adapters should be compared with the old model, not only the new one. Of five adapter variants, only same-family LLM bridges beat the old model, and only by a negligible margin. Third, window re-ranking cost can be priced from the old index alone; pre-registered replays on all 8,841,823 passages confirmed the prediction on all three tested pairs. Workload skew also matters: across 36 further pre-registered Zipf replays, the planned family matched on 32. These findings yield three pre-migration rules: whether reuse is worthwhile, which strategy to use, and how deep a window to take. The depth rule priced every window that reached target quality to within 4 parts in 10^5 of the corpus. On NQ, a pre-committed plan selected the family on 10 of 11 pairs and priced every window exactly. Quality inputs transferred less reliably across corpus scale, so the model gap and window quality loss must be measured on the serving index.

Figures & tables

Explore similar work

May 8, 2026

Do not copy and paste! Rewriting strategies for code retrieval

Embedding-based code retrieval often suffers when encoders overfit to surface syntax. Prior work mitigates this by using LLMs to rephrase queries and corpora into a normalized style, but leaves two questions open: how much representational shift helps, and when is the per-query LLM call justified? We study a hierarchy of three rewriting strategies: stylistic rephrasing, NL-enriched PseudoCode, and full Natural-Language transcription, under joint query-corpus (QC, online) and corpus-only (C, offline) augmentation, across six CoIR benchmarks, five encoders, and three rewriters spanning independent model families (Qwen, DeepSeek, Mistral). We are the first to evaluate NL-enriched PseudoCode and snippet-level Natural Language as direct retrieval representations, rather than as transient intermediates. Full NL rewriting with QC yields the largest gains (+0.51 absolute NDCG@10 on CT-Contest for MoSE-18), while corpus-only rewriting degrades retrieval in 56 of 90 configurations, about 62%. We introduce two diagnostics, Delta H, token entropy, and Delta s, embedding cosine, and show that Delta H predicts retrieval gain under QC across all three rewriter families: pooled Spearman rho = +0.436, p < 0.001 on DeepSeek+Codestral; rho = +0.593 on Codestral alone; rho = +0.356 on Qwen. This establishes Delta H as a cheap, rewriter-agnostic proxy for deciding when rewriting pays off before running retrieval. Our analysis reframes LLM rewriting as a cost-benefit decision: it is most effective as a remediation layer for lightweight encoders on code-dominant queries, with diminishing returns for strong encoders or NL-heavy queries.
Oct 9, 2026

Simple Linear Corrections for Compression in Late Interaction

Late-interaction (multi-vector) models represent documents using a set of token-level vectors, providing a middle ground between cross-encoders and dense encoders in terms of quality and cost of embedding. However, compared to the latter, the indices are costly to store and score. Pooling and pruning based compression techniques are deployed widely but deteriorate in quality noticeably with aggressive compression. We investigate whether a lightweight change to the scoring function can recover retrieval quality after document-vector compression. For each combination of encoder, compressor, and vector budget, we learn a global linear correction by distilling the uncompressed model's score distributions over candidate documents. The encoder and compressor remain frozen, and the correction can be applied to each query at search time or once, offline, to the stored vectors. We evaluate the method with ColBERTv2 and Jina v4 on MS MARCO and BEIR, and with ColPali2 on the ViDoRe v3 visual document retrieval benchmark. Experiments cover four training-free compression methods, multiple vector budgets, in-domain adaptation, and transfer from MS MARCO to BEIR. In the in-domain setting, the correction improves over baseline compression in 154 of 160 BEIR settings, while transfer from MS MARCO is more variable across models and datasets. We also find that matrices trained with synthetic queries can improve over baseline compression on ViDoRe v3. These results show that a small learned correction can recover some of the quality lost to compression without retraining the encoder or recompressing the documents.
Sep 4, 2026

Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability

Model upgrades are routine; memory migrations are not. An agent can keep the same memory store and still forget: a new model may interpret old notes differently, mixed embedding versions may break retrieval, and repair may fail without the original evidence. We compare memory as the same history is preserved verbatim for long-context reading (LC-RAW), divided into chunks for retrieval-augmented generation (RAG), compressed by a model into natural-language notes (NOTES), or normalized into a fixed-schema knowledge graph (KG-fixed). The study uses 48 synthetic histories with randomized answer codes, exact scoring, and two open-weight models with sub 10 billion parameters. Our measurements show that fixed-schema structures transfer reliably, with KG-fixed accuracy changing by only +0.0004±0.0020+0.0004 \pm 0.0020 following a writer swap. Conversely, compressed NOTES exhibit high model coupling, with accuracy shifting asymmetrically by +9.91+9.91 or −13.28-13.28 percentage points depending on the specific migration direction. In RAG systems, partial embedding migrations using a 50/50 mixed index capture only a 4.96-point accuracy improvement, forfeiting the majority of the 11.90-point gain achieved through full re-embedding. Diagnostic decomposition attributes 80% (0.467±0.0140.467 \pm 0.014) of the NOTES accuracy deficit to information lost during initial construction, whereas retrieval failures drive 81% (0.364±0.0120.364 \pm 0.012) of the RAG deficit. Finally, store-only repair of NOTES fails to reach a 90% performance recovery target in all 48 test cases, whereas retaining the raw source history enables successful recovery in 34 of 48 cases for one tested direction. These findings highlight the necessity of direction-specific migration testing, strict embedding space isolation, and the retention of source histories for memory repair.