mlsanityData to 14 Oct 2026

Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks

arXiv 2511.09373 ↗First posted 12 Nov 2025cs.SE cs.CL cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks. Routing user queries to the appropriate LLMs can therefore help improve response quality while reducing cost. Prior work, however, has focused mainly on general-purpose LLM routing via black-box models. We introduce Routesplain, the first LLM router for software-related tasks, including multilingual code generation and repair, input/output prediction, and computer science QA. Unlike existing routing approaches, Routesplain first extracts human-interpretable concepts from each query (e.g., task, domain, reasoning complexity) and only routes based on these concepts, thereby providing intelligible, faithful rationales. We evaluate Routesplain on 16 state-of-the-art LLMs across eight software-related tasks; Routesplain outperforms individual models both in terms of accuracy and cost, and equals or surpasses all black-box baselines, with concept-level intervention highlighting avenues for further router improvements.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 41 of its 46 references that are in the map. First posted on arXiv 12 Nov 2025.

Builds on

41 of 46 references.

References · 41

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  5. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  6. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  7. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
  8. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  9. 2020Concept Bottleneck Modelscited by 1,032
  10. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928
  11. 2021Probing Classifiers: Promises, Shortcomings, and Advancescited by 876
  12. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
29 more
  1. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  2. 2019Designing and Interpreting Probes with Control Taskscited by 640
  3. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  4. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  5. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 487
  6. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 452
  7. 2025Reasoning Models Don't Always Say What They Thinkcited by 415
  8. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 372
  9. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
  10. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 300
  11. 2023Label-Free Concept Bottleneck Modelscited by 285
  12. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinementcited by 247
  13. 2024RouterBench: A Benchmark for Multi-LLM Routing Systemcited by 238
  14. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 197
  15. 2023Large Language Model Routing with Benchmark Datasetscited by 172
  16. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 145
  17. 2023Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modelingcited by 95
  18. 2023Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanationscited by 85
  19. 2025MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluationcited by 79
  20. 2022SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarizationcited by 61
  21. 2024EmbedLLM: Learning Compact Representations of Large Language Modelscited by 48
  22. 2022Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systemscited by 44
  23. 2025IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theorycited by 40
  24. 2023Coarse-to-Fine Concept Bottleneck Modelscited by 31
  25. 2024Smoothie: Label Free Language Model Routingcited by 31
  26. 2024Code Representation Learning At Scalecited by 26
  27. 2024PickLLM: Context-Aware RL-Assisted Large Language Model Routingcited by 13
  28. 2025TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Taskscited by 9
  29. 2025Lookahead Routing for Large Language Modelscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Poolscited by 1
  2. 2026Routing Without Embeddings: Fast And Interpretable Routing With Regular Expressionscited by 0