Pith. sign in

REVIEW 8 cited by

SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2207.02578 v2 pith:HPUJUJ5L submitted 2022-07-06 cs.IR

classification cs.IR
keywords pre-trainingsimlmpassagedenseretrievalbottlenecklanguagemodel
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper, we propose SimLM (Similarity matching with Language Model pre-training), a simple yet effective pre-training method for dense passage retrieval. It employs a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training. We use a replaced language modeling objective, which is inspired by ELECTRA, to improve the sample efficiency and reduce the mismatch of the input distribution between pre-training and fine-tuning. SimLM only requires access to unlabeled corpus, and is more broadly applicable when there are no labeled data or queries. We conduct experiments on several large-scale passage retrieval datasets, and show substantial improvements over strong baselines under various settings. Remarkably, SimLM even outperforms multi-vector approaches such as ColBERTv2 which incurs significantly more storage cost. Our code and model check points are available at https://github.com/microsoft/unilm/tree/master/simlm .

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RaDeR: Reasoning-aware Dense Retrieval Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A math-trained dense retriever and reranker, built from MCTS reasoning trajectories and self-reflection, outperforms strong baselines on reasoning-intensive retrieval benchmarks and beats BM25 on chain-of-thought queries.

  2. O1 Embedder: Let Retrievers Think Before Action

    cs.CL 2025-02 conditional novelty 6.0 of 10

    A jointly trained retriever that first generates query thoughts and then encodes them improves accuracy on 12 retrieval benchmarks.

  3. Matryoshka Re-Ranker: A Flexible Re-Ranking Architecture With Configurable Depth and Width

    cs.CL 2025-01 conditional novelty 6.0 of 10

    A single LLM re-ranker can be configured at runtime to different depths and widths, with training tricks that keep compressed variants close to full-scale accuracy.

  4. AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

    cs.IR 2024-12 conditional novelty 6.0 of 10

    AIR-Bench uses LLMs to generate retrieval test data over 69 datasets, 9 domains and 13 languages, and reports a 0.82 rank correlation between model rankings on its generated MS MARCO set and human-labeled MS MARCO.

  5. State Space Models are Strong Text Rerankers

    cs.CL 2024-12 conditional novelty 5.0 of 10

    Mamba-1 and Mamba-2 rerankers match comparably sized transformers on ranking accuracy but are less efficient in training and inference, with Mamba-2 improving on both fronts.

  6. GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval

    cs.IR 2025-06 conditional novelty 4.0 of 10

    GOLFer filters hallucinated sentences from small-LM-generated hypothetical documents and reweights the rest into the query, improving retrieval at lower cost than large LLM expansion.

  7. Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion

    cs.IR 2025-06 conditional novelty 4.0 of 10

    Exp4Fuse improves sparse retrieval by fusing the ranked lists from the original query and an LLM-expanded query using a modified reciprocal rank fusion.

  8. LLMs are Also Effective Embedding Models: An In-depth Overview

    cs.CL 2024-12 conditional novelty 2.0 of 10

    A structured survey of using decoder-only LLMs as text embedding models, covering prompting, fine-tuning, data construction, benchmarks, and open problems.

Pith tools