mlsanityData to 7 Oct 2026

UltraIF: Advancing Instruction Following from the Wild

arXiv 2502.04153 ↗First posted 6 Feb 2025cs.CL cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Instruction-following made modern large language models (LLMs) helpful assistants. However, the key to taming LLMs on complex instructions remains mysterious, for that there are huge gaps between models trained by open-source community and those trained by leading companies. To bridge the gap, we propose a simple and scalable approach UltraIF for building LLMs that can follow complex instructions with open-source data. UltraIF first decomposes real-world user prompts into simpler queries, constraints, and corresponding evaluation questions for the constraints. Then, we train an UltraComposer to compose constraint-associated prompts with evaluation questions. This prompt composer allows us to synthesize complicated instructions as well as filter responses with evaluation questions. In our experiment, for the first time, we successfully align LLaMA-3.1-8B-Base to catch up with its instruct version on 5 instruction-following benchmarks without any benchmark information, using only 8B model as response generator and evaluator. The aligned model also achieved competitive scores on other benchmarks. Moreover, we also show that UltraIF could further improve LLaMA-3.1-8B-Instruct through self-alignment, motivating broader use cases for the method. Our code is available at https://github.com/kkk-an/UltraIF.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 6 Feb 2025.

Builds on

14 of 27 references.

References · 14

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  7. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  8. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  9. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 484
  10. 2023Rethinking Benchmark and Contamination for Language Models with Rephrased Samplescited by 192
  11. 2024Noise Contrastive Alignment of Language Models with Explicit Rewardscited by 85
  12. 2024Towards a Unified View of Preference Learning for Large Language Models: A Surveycited by 17
2 more
  1. 2024Smaller Language Models Are Better Instruction Evolverscited by 6
  2. 2024Evolutionary Contrastive Distillation for Language Model Alignmentcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 11; 2026: 7.

18 papers.

Sort:

By area:

  1. 2025OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignmentcited by 118
  2. 2026Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Trainingcited by 45
  3. 2025VerIF: Verification Engineering for Reinforcement Learning in Instruction Followingcited by 43
  4. 2026RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Followingcited by 19
  5. 2025Incentivizing Reasoning for Advanced Instruction-Following of Large Language Modelscited by 17
  6. 2025RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Datacited by 11
  7. 2025Large Language Models as Computable Approximations to Solomonoff Inductioncited by 6
  8. 2025IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewardscited by 6
  9. 2026Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skillscited by 6
  10. 2025Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Followingcited by 3
  11. 2025AHAMask: Reliable Task Specification for Large Audio Language Models without Instructionscited by 3
  12. 2025ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Modelscited by 3
6 more
  1. 2025From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decompositioncited by 3
  2. 2026RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domainscited by 3
  3. 2026SEIF: Self-Evolving Reinforcement Learning for Instruction Followingcited by 1
  4. 2025TCIA: A Task-Centric Instruction Augmentation Method for Instruction Finetuningcited by 0
  5. 2026LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Modelscited by 0
  6. 2026Cross-Relational Preference Learning for Better LLM Instruction Followingcited by 0