# Goal-Conditioned Supervised Learning for LLM Fine-Tuning

arXiv: https://arxiv.org/abs/2605.16345 · HTML: https://mlsanity.com/paper/2605.16345/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 42 of its 48 references that are in the map.
- First posted on arXiv 8 May 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 30 of 42)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://mlsanity.com/paper/2106.02039/) (2021)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [KTO: Model Alignment as Prospect Theoretic Optimization](https://mlsanity.com/paper/2402.01306/) (2024)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [Many-Shot In-Context Learning](https://mlsanity.com/paper/2404.11018/) (2024)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [Goal-Conditioned Reinforcement Learning: Problems and Solutions](https://mlsanity.com/paper/2201.08299/) (2022)
- [Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions](https://mlsanity.com/paper/1912.02875/) (2019)
- [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF](https://mlsanity.com/paper/2310.05344/) (2023)
- [When does return-conditioned supervised learning work for offline reinforcement learning?](https://mlsanity.com/paper/2206.01079/) (2022)
- [A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems](https://mlsanity.com/paper/2308.08434/) (2023)
- [On Softmax Direct Preference Optimization for Recommendation](https://mlsanity.com/paper/2406.09215/) (2024)
- [Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)](https://mlsanity.com/paper/2507.12856/) (2025)
- [Mercury: A Code Efficiency Benchmark for Code Large Language Models](https://mlsanity.com/paper/2402.07844/) (2024)

## Abstract (arXiv)

Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into online and offline paradigms. Online methods, such as RL-based alignment, can directly optimize outcome quality but typically rely on external reward models and iterative rollouts, making them costly and difficult to deploy in many cases. Offline methods are more efficient, but prevailing approaches such as supervised fine-tuning (SFT) and direct preference optimization (DPO) remain limited: SFT typically collapses graded feedback into binary supervision, while DPO depends on paired preference data that is often unavailable or expensive to construct. In this paper, we propose goal-conditioned supervised learning (GCSL) as an offline fine-tuning framework for LLMs. Our core idea is to treat feedback signals directly as an explicit goal and train the model, purely through supervised learning, to generate responses that achieve that goal. To better exploit graded feedback, we further introduce a novel goal formulation that defines learning as consistently pursuing outcomes above a target quality threshold, rather than imitating samples from a selected high-quality subset. This design mitigates the bounded-learning effect by learning transferable patterns of meeting or exceeding quality thresholds. We also propose natural-language goal representations to further connect these patterns to the LLM's pretrained knowledge and generalization capabilities. We evaluate our method on three tasks: non-toxic generation, code generation, and LLM for recommendation. Results show that our approach consistently outperforms standard offline fine-tuning baselines while retaining the efficiency, scalability, and simple data requirements of supervised learning.