Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process (2025.acl-long)
Copied to clipboard
| Challenge: | Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models with human preferences post pre-training. |
| Approach: | They propose to combine Supervised Fine-Tuning and Preference Optimization (PO) with two sub-processes defined at token level within the Markov Decision Process (MDP) |
| Outcome: | The proposed process performs comparably or even superiorly to SFT and some typical PO methods across several tasks, particularly those requires generation, reasoning, and fact-following abilities. |
Similar Papers
Select Before Use: On the Importance of Reference Model Selection in Preference Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Supervised Fine-Tuning (SFT) is used as the initialization and reference model for subsequent preference alignment. |
| Approach: | They propose to use RewardRank to estimate initial implicit alignment between reference model and preference objective to ensure LLMs generate safe, helpful, and instruction-aligned content. |
| Outcome: | Empirical evidence shows that using the selected model as reference can gain up to 67.6% relative increase on length-controlled win rate compared to baselines. |
A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models are pre-trained on trillions of tokens and instruction-tuned or aligned to specific preferences. |
| Approach: | They propose guidelines to help researchers perform more effective parameter-efficient LLM alignment. |
| Outcome: | The proposed methods outperform preference optimization and outperformed pre-trained models on three key axes. |
Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks (2025.acl-srw)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel in math reasoning problemsolving, text generation, summarization, creative writing, among other tasks. |
| Approach: | They evaluate Direct Preference Optimization and its variants for aligning Large Language Models with human preferences. |
| Outcome: | The proposed alignment methods achieve near-optimal performance even with smaller subsets of training data. |
ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection (2026.findings-acl)
Copied to clipboard
| Challenge: | Traditional fine-tuning ignores one-to-many nature of language, leading to overfitting . authors propose a method to fine- tune LLMs by leveraging tokens. |
| Approach: | They propose a method to fine-tune Large Language Models by leveraging tokens to mask low-probability tokens. |
| Outcome: | The proposed method outperforms baselines on general reasoning and mathematical benchmarks. |
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training (2026.findings-acl)
Copied to clipboard
Rui Zhang, Hongwei Li, Yun Shen, Xinyue Shen, Wenbo Jiang, Guowen Xu, Yang Liu, Michael Backes, Yang Zhang
| Challenge: | Misaligned large language models can magnify harm by exploiting them to undermine safety . et al., 2022b; Bai e.t., 2023): misalignment, realignment and model-specific resistance are important . |
| Approach: | They evaluate four methods to identify a mechanism asymmetry between attack and defense . they find that ORPO is most effective for misalignment, but DPO excels in realignment . |
| Outcome: | The proposed methods show a mechanism asymmetry between attack and defense . the proposed methods excel in realignment, but at the expense of model utility . |
Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have greatly improved natural language understanding and generation. |
| Approach: | They train a wide range of base models on a variety of datasets including code generation, mathematical reasoning, and general-domain tasks. |
| Outcome: | The results show that training–task synergies persist across all models while others vary substantially, emphasizing the importance of model-specific strategies. |
A Layer-wise Analysis of Supervised Fine-Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning ignore depth-dependent heterogeneity of instruction-following . a critical gap remains in understanding where these changes occur across the model's depth and which layers are essential for instruction- following. |
| Approach: | They propose a method which selectively updates critical intermediate layers . they show that effective alignment is architecturally localized rather than distributed . |
| Outcome: | The proposed method outperforms standard LoRA up to 10.2% on GSM8K with reduced parameter overhead. |
Self-Evolution Fine-Tuning for Policy Optimization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent years have showcased the remarkable capabilities and performance of large language models (LLMs) across a broad range of tasks. |
| Approach: | They propose supervised fine-tuning (SEFT) for LLM alignment to eliminate the need for annotated samples while retaining the stability and efficiency of SFT. |
| Outcome: | The proposed method eliminates the need for annotated samples while maintaining the stability and efficiency of SFT. |
Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning (2025.acl-long)
Copied to clipboard
| Challenge: | Results show that supervised fine-tuning and preference finetunation are the most efficient approaches for large language models. |
| Approach: | They propose to use Supervised Finetuning and Preference Finetunes to optimize training data budgets for Large Language Models. |
| Outcome: | The proposed approach improves performance on math tasks by 15% on the most expensive model, 1,000 examples. |
Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to improve data quality face limitations in static dataset curation that fail to adapt to evolving model capabilities. |
| Approach: | They propose a self-evolving framework that uses model-aware data selection and context-preserving data refinement to improve LLM performance. |
| Outcome: | The proposed framework improves the quality of seed data and boosts LLM’s performance with improving accuracy by 7.15% on average while maintaining the original dataset scale. |