emrekuruu
/

RetrievalRouter-lambda-l30

@@ -1,199 +1,155 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
+license: mit
+language:
+- en
+base_model:
+- Qwen/Qwen3-0.6B-Base
 library_name: transformers
+pipeline_tag: text-classification
+tags:
+- retrieval
+- document-retrieval
+- information-retrieval
+- routing
+- RAG
+- query-routing
+- late-interaction
+- lora
+- peft
+datasets:
+- emrekuruu/FinReport
+- emrekuruu/FinSlides
+- emrekuruu/FinQA
+- emrekuruu/ConvFinQA
+- emrekuruu/VQAonBD
+- emrekuruu/TATDQA
+- emrekuruu/ArxivQA
+- emrekuruu/Wiki-ss
+- emrekuruu/MP-DocVQA
+- emrekuruu/SciQAG
+- emrekuruu/DUDE
+metrics:
+- ndcg
 ---
+# RetrievalRouter (λ=0.3)
+Official checkpoint from **RetrievalRouter: Joint Modality and Architecture Selection for
+Document Retrieval** (EMNLP 2026). Given only the **query text**, RetrievalRouter predicts
+*which retrieval pipeline* — across **modality** (text vs. multimodal) and **architecture**
+(lexical, dense, or late-interaction rerank) — to run for that query.
+- 📄 Paper: https://arxiv.org/pdf/2608.23176
+- 💻 Code: https://github.com/emrekuruu/retrieval-router
+- 🤗 Collection (all checkpoints + datasets): https://huggingface.co/collections/emrekuruu/retrieval-router
+## Motivation
+Retrieval pipelines differ in **modality** (search over text, or over page images) and
+**architecture** (cheap dense search, or expensive late-interaction). The accurate ones are
+slow; the fast ones miss evidence on hard documents. And which one fails depends on the query —
+a text pipeline can't answer "what's the red curve in Figure 3?", but a multimodal one is
+overkill for a plain factoid. Across 11 benchmarks, **no single pipeline wins on everything**.
+RetrievalRouter picks the cheapest pipeline that can still answer each query, so easy queries
+stay fast and hard ones still get the heavy pipeline.
+## What this model is for
+This is a **router, not a retriever**. It takes a query and predicts which of five retrieval
+pipelines to run — in about 15 ms, before any search happens. You then run the chosen pipeline
+to fetch documents.
+Use it when you keep several retrieval setups over the same corpus and want to run the expensive
+ones only when they help. Pick the checkpoint by **λ**: `0.0` for best accuracy, `1.0` for best
+speed, in between to trade off.
+It doesn't rank or read documents itself, and assumes your indices already exist. Trained on
+English financial, scientific, and open-domain documents; other domains and languages are
+untested.
+## This checkpoint
+**Trained with λ=0.3** — a **balanced** objective (λ=0.3), trading a controlled amount of accuracy for lower latency between the quality-only (λ=0.0) and latency-only (λ=1.0) endpoints.
+| Checkpoint | λ | Objective |
+|---|---|---|
+| [`RetrievalRouter-lambda-l00`](https://huggingface.co/emrekuruu/RetrievalRouter-lambda-l00) | 0.0 | Accuracy only |
+| [`RetrievalRouter-lambda-l10`](https://huggingface.co/emrekuruu/RetrievalRouter-lambda-l10) | 0.1 | Accuracy-leaning |
+| [`RetrievalRouter-lambda-l30`](https://huggingface.co/emrekuruu/RetrievalRouter-lambda-l30) | 0.3 | Balanced |
+| [`RetrievalRouter-lambda-l50`](https://huggingface.co/emrekuruu/RetrievalRouter-lambda-l50) | 0.5 | Balanced |
+| [`RetrievalRouter-lambda-l70`](https://huggingface.co/emrekuruu/RetrievalRouter-lambda-l70) | 0.7 | Latency-leaning |
+| [`RetrievalRouter-lambda-l100`](https://huggingface.co/emrekuruu/RetrievalRouter-lambda-l100) | 1.0 | Latency only |
+## Routing arms
+| Index | Arm (config name) | Paper name | Modality | Architecture |
+|---|---|---|---|---|
+| 0 | `MULTIMODAL_RERANK` | MM-Rerank | Multimodal | Dense → late-interaction rerank |
+| 1 | `MULTIMODAL-SINGLE` | MM-Dense | Multimodal | Single-vector dense |
+| 2 | `TEXT_RERANK` | Text-Rerank | Text | Dense → late-interaction rerank |
+| 3 | `TEXT-SINGLE` | Text-Dense | Text | Single-vector dense |
+| 4 | `BM25` | BM25 | Text | Lexical |
+The action space is these five arms. Two further pipelines evaluated in the paper (Text-Late,
+MM-Late) are reported as static reference baselines but never routed to.
+## Architecture
+- **Encoder:** [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) with LoRA
+  adapters on the attention and feed-forward projections (merged into these weights).
+- **Pooling:** mean-pool over the final hidden states → a 1024-d query representation.
+- **Head:** a single linear layer → logits over the five arms; softmax gives the routing policy.
+- Custom modeling code ships in the repo and loads via `trust_remote_code=True`.
+## Usage
+```python
+import torch
+from transformers import AutoModel, AutoTokenizer
+repo = "emrekuruu/RetrievalRouter-lambda-l30"
+tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
+model = AutoModel.from_pretrained(repo, trust_remote_code=True).eval()
+inputs = tokenizer("In figure 3, what does the red dashed curve represent?",
+                   return_tensors="pt", truncation=True, max_length=128)
+with torch.no_grad():
+    logits = model(**inputs)["logits"]              # shape [1, 5]
+arm = model.config.strategy_names[logits.softmax(-1).argmax(-1).item()]
+print(arm)   # e.g. "MULTIMODAL_RERANK" -> run that pipeline for this query
+```
+The router returns **which retrieval pipeline to run**, not documents. You then execute the
+selected pipeline against your own indices.
+## Training
+Trained against **soft targets** from a per-query reward vector over the five arms, rather than a
+single hard best-pipeline label (pipelines frequently tie on nDCG@5, and hard labels inject
+noise). The reward combines accuracy and efficiency,
+$$ r_i(q) = (1-\lambda)\, s_i(q) + \lambda\,(1 - \ell_i(q)), $$
+where $s_i(q)$ is the arm's nDCG@5 and $\ell_i(q)$ its per-query normalized latency. The reward
+vector becomes a target distribution via a low-temperature softmax (τ=0.1), and the router
+minimizes the KL divergence to it. **λ is the only knob** that differs across the checkpoints
+above. Training data spans **85,103 queries across 11 benchmarks**.
+## Results (headline)
+Against the strongest static pipeline, RetrievalRouter is **+2.5% nDCG@5 and 12.4× faster**.
+Against the prior adaptive strategy-selection baseline
+([`emrekuruu/Baseline`](https://huggingface.co/emrekuruu/Baseline)), it achieves significantly
+higher nDCG@5 in accuracy-oriented settings and matches or numerically beats it on both nDCG@5
+and latency in latency-oriented settings. See the paper for full tables and significance tests.
+## Citation
+```bibtex
+@inproceedings{kuru2026retrievalrouter,
+  title     = {RetrievalRouter: Joint Modality and Architecture Selection for Document Retrieval},
+  author    = {Kuru, Emre and Keskin, Mehmet Onur and Farahbakhsh, Reza and Crespi, Noel},
+  booktitle = {Proceedings of EMNLP 2026},
+  year      = {2026}
+}
+```