mlsanityData to 14 Oct 2026

DUALVIEW: Leveraging Broad and Output-Specific Evidence for LLM-based Multi-Output Text Regression

arXiv 2610.19206 ↗First posted 13 Oct 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

While work on LLM-based regression has largely focused on scalar prediction, multi-output text regression remains less explored. We present DualView, a parameter-efficient approach to leverage LLMs for multi-output text regression. method first extracts broad and output-specific representations from a frozen LLM, then uses a dual-branch architecture to produce the full score vector. Across five heterogeneous regression tasks and eight LLMs (up to 122B), DualView outperforms seven supervised regression baselines while requiring 82--1842 times fewer fitted parameters than the three strongest baselines. These improvements extend across individual output dimensions and persist even with limited training data. Notably, DualView using a smaller open-weight LLM can outperform unsupervised prediction with Gemini 3.1 Pro. Controlled ablations show that broad and output-specific evidence provide complementary predictive benefits, while lightweight shared predictors achieve strong performance with fewer trainable parameters.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 62 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

40 of 62 references.

References · 40

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  3. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  4. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  5. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  6. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
  7. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
  8. 2024Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Expertscited by 376
  9. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 363
  10. 2022Multi-Task Learning as a Bargaining Gamecited by 215
  11. 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 210
  12. 2024Better by Default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Datacited by 92
28 more
  1. 2024From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examplescited by 57
  2. 2024How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmarkcited by 43
  3. 2024LMUnit: Fine-grained Evaluation with Natural Language Unit Testscited by 33
  4. 2025Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluationcited by 30
  5. 2024Robust Multi-Task Learning with Excess Riskscited by 24
  6. 2025Selective Task Group Updates for Multi-Task Optimizationcited by 17
  7. 2025TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judgecited by 17
  8. 2025DSCodeBench: A Realistic Benchmark for Data Science Code Generationcited by 17
  9. 2024Regression-aware Inference with LLMscited by 14
  10. 2025Rethinking Creativity Evaluation: A Critical Analysis of Existing Creativity Evaluationscited by 14
  11. 2024Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewardscited by 12
  12. 2025Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languagescited by 11
  13. 2025Bradley-Terry and Multi-Objective Reward Modeling Are Complementarycited by 11
  14. 2025Regression Language Models for Codecited by 11
  15. 2025Quantile Regression with Large Language Models for Price Predictioncited by 10
  16. 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddingscited by 7
  17. 2026LLMs Know More About Numbers than They Can Saycited by 7
  18. 2026Eliciting Numerical Predictive Distributions of LLMs Without Autoregressioncited by 6
  19. 2024Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Modelscited by 5
  20. 2024A Problem-Oriented Perspective and Anchor Verification for Code Optimizationcited by 4
  21. 2025Teaching Metric Distance to Discrete Autoregressive Language Modelscited by 4
  22. 2025Feeding Two Birds or Favoring One? Adequacy-Fluency Tradeoffs in Evaluation and Meta-Evaluation of Machine Translationcited by 4
  23. 2023Counterfactual Augmentation for Multimodal Learning Under Presentation Biascited by 2
  24. 2026REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judgecited by 2
  25. 2026RELISH: LLM REgression with a Latent Iterative State Headcited by 2
  26. 2026Text-to-Distribution Prediction with Quantile Tokens and Neighbor Contextcited by 1
  27. 2026Multi-Task Bayesian In-Context Learningcited by 1
  28. 2026Enhancing Numerical Prediction in LLMs via Smooth MMD Alignmentcited by 1

Built on by

Not cited yet.