mlsanityData to 7 Oct 2026

Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models

arXiv 2404.02823 ↗First posted 3 Apr 2024cs.CL cs.AI cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

The ability of large language models (LLMs) to follow instructions is crucial to real-world applications. Despite recent advances, several studies have highlighted that LLMs struggle when faced with challenging instructions, especially those that include complex constraints, hindering their effectiveness in various tasks. To address this challenge, we introduce Conifer, a novel instruction tuning dataset, designed to enhance LLMs to follow multi-level instructions with complex constraints. Utilizing GPT-4, we curate the dataset by a series of LLM-driven refinement processes to ensure high quality. We also propose a progressive learning scheme that emphasizes an easy-to-hard progression, and learning from process feedback. Models trained with Conifer exhibit remarkable improvements in instruction-following abilities, especially for instructions with complex constraints. On several instruction-following benchmarks, our 7B model outperforms the state-of-the-art open-source 7B models, even exceeds the performance of models 10 times larger on certain metrics. All the code and Conifer dataset are available at https://www.github.com/ConiferLM/Conifer.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 31 of its 49 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

31 of 49 references.

References · 31

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  7. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  8. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  9. 2023Let's Verify Step by Stepcited by 3,598
  10. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  11. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  12. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
19 more
  1. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  2. 2023LIMA: Less Is More for Alignmentcited by 1,080
  3. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  4. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  5. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  6. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 712
  7. 2020Aligning AI With Shared Human Valuescited by 706
  8. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  9. 2023Zephyr: Direct Distillation of LM Alignmentcited by 498
  10. 2023What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuningcited by 354
  11. 2023OpenChat: Advancing Open-source Language Models with Mixed-Quality Datacited by 250
  12. 2023Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2cited by 227
  13. 2023Rethinking Benchmark and Contamination for Language Models with Rephrased Samplescited by 192
  14. 2023Skywork: A More Open Bilingual Foundation Modelcited by 110
  15. 2024Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuningcited by 85
  16. 2023Evaluating Large Language Models on Controlled Generation Taskscited by 73
  17. 2023The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactionscited by 45
  18. 2023MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Followingcited by 30
  19. 2020POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-trainingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 12; 2026: 4.

26 papers.

Sort:

By area:

  1. 2024LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMscited by 142
  2. 2025Checklists Are Better Than Reward Models For Aligning Language Modelscited by 115
  3. 2024TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generationcited by 62
  4. 2025AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarioscited by 44
  5. 2024A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applicationscited by 27
  6. 2024Do LLMs estimate uncertainty well in instruction-following?cited by 26
  7. 2024Do LLMs "know" internally when they follow instructions?cited by 25
  8. 2024SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Modelscited by 23
  9. 2025Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generationcited by 20
  10. 2025Incentivizing Reasoning for Advanced Instruction-Following of Large Language Modelscited by 17
  11. 2024Revisiting the Superficial Alignment Hypothesiscited by 12
  12. 2024Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leapscited by 12
14 more
  1. 2025Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencodercited by 11
  2. 2025RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Datacited by 11
  3. 2024MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmarkcited by 8
  4. 2025PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Modelscited by 8
  5. 2024Baichuan Alignment Technical Reportcited by 6
  6. 2025Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Followingcited by 6
  7. 2025DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulationcited by 4
  8. 2025Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Followingcited by 3
  9. 2026ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Followingcited by 3
  10. 2025Enhancing Complex Instruction Following for Large Language Models with Mixture-of-Contexts Fine-tuningcited by 2
  11. 2025Training with Pseudo-Code for Instruction Followingcited by 1
  12. 2026SEIF: Self-Evolving Reinforcement Learning for Instruction Followingcited by 1
  13. 2026Cross-Relational Preference Learning for Better LLM Instruction Followingcited by 0
  14. 2026ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modelingcited by 0