Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that reparameterizes reward functions in reinforcement learning from human feedback (RLHF) to enhance simplicity and training stability. In this work, we propose SimPO, a simpler yet more effective approach. The effectiveness of SimPO is attributed to a key design: using the _average_ log probability of a sequence as the implicit reward. This reward formulation better aligns with model generation and eliminates the need for a reference model, making it more compute and memory efficient. Additionally, we introduce a target reward margin to the Bradley-Terry objective to encourage a larger margin between the winning and losing responses, further improving the algorithm's performance. We compare SimPO to DPO and its latest variants across various state-of-the-art training setups, including both base and instruction-tuned models such as Mistral, Llama 3, and Gemma 2. We evaluate on extensive chat-based evaluation benchmarks, including AlpacaEval 2, MT-Bench, and Arena-Hard. Our results demonstrate that SimPO consistently and significantly outperforms existing approaches without substantially increasing response length. Specifically, SimPO outperforms DPO by up to 6.4 points on AlpacaEval 2 and by up to 7.5 points on Arena-Hard. Our top-performing model, built on Gemma-2-9B-it, achieves a 72.4\% length-controlled win rate on AlpacaEval 2, a 59.1\% win rate on Arena-Hard, and ranks 1st on Chatbot Arena among $

Although humans inherently have diverse values, current large language model (LLM) alignment methods often assume that aligning LLMs with the general public's preferences is optimal. A major challenge in adopting a more individualized approach to LLM alignment is its lack of scalability, as it involves repeatedly acquiring preference data and training new reward models and LLMs for each individual's preferences. To address these challenges, we propose a new paradigm where users specify what they value most within the system message, steering the LLM's generation behavior to better align with the user's intentions. However, a naive application of such an approach is non-trivial since LLMs are typically trained on a uniform system message (e.g., "You are a helpful assistant"), which limitstheir ability to generalize to diverse, unseen system messages. To improve this generalization, we create Multifaceted Collection, augmenting 66k user instructions into 197k system messages through hierarchical user value combinations. Using this dataset, we train a 7B LLM called Janus and test it on 921 prompts from 5 benchmarks (AlpacaEval 2.0, FLASK, Koala, MT-Bench, and Self-Instruct)by adding system messages that reflect unseen user values. JANUS achieves tie+win rate of 75.2%, 72.4%, and 66.4% against Mistral 7B Instruct v0.2, GPT-3.5 Turbo, and GPT-4, respectively. Unexpectedly, on three benchmarks focused on response helpfulness (AlpacaEval 2.0, MT-Bench, Arena Hard Auto v0.1), JANUS also outperforms LLaMA 3 8B Instruct by a +4.0%p, +0.1%p, +3.0%p margin, underscoring that training with a vast array of system messages could also enhance alignment to the general public's preference as well. Our code, dataset, benchmark, and models are available at https://lklab.kaist.ac.kr/Janus/.

Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that preference data is clean and that all labels are equally reliable. In practice, large-scale preference datasets contain substantial noise due to annotator mistakes, inconsistent instructions, varying expertise, and even adversarial or low-effort feedback. This mismatch between recorded labels and ground-truth preferences can misguide training and degrade model performance. To address this issue, we introduce Robust Enhanced Policy Optimization (RE-PO), which uses an expectation-maximization procedure to infer the posterior correctness of each label and then adaptively reweight data points in the training loss to mitigate label noise. We further generalize this idea by establishing a theoretical link between arbitrary preference losses and their underlying probabilistic models, enabling a systematic transformation of existing alignment algorithms into robust counterparts and elevating RE-PO from a single method to a general framework for robust preference alignment. Theoretically, we prove that, under a perfectly calibrated model, RE-PO recovers the true noise level of the dataset. Empirically, we show that RE-PO consistently improves four state-of-the-art alignment methods (DPO, IPO, SimPO, and CPO); when applied to Mistral and Llama 3 models, the RE-PO-enhanced variants increase AlpacaEval 2 win rates by up to 7.0 percent over their respective baselines.

Direct Preference Optimization (DPO) has emerged as an important approach for learning from human preferences in aligning large language models (LLMs). However, collecting human preference data is costly and inefficient, motivating methods to reduce the required annotations. In this work, we investigate the impact of \emph{preference variance} (PVar), which measures the variance in model preferences when comparing pairs of responses, on the effectiveness of DPO training. We provide a theoretical insight by establishing an upper bound on the DPO gradient norm for any given prompt, showing it is controlled by the PVar of that prompt. This implies that prompts with low PVar can only produce small gradient updates, making them less valuable for learning. We validate this finding by fine-tuning LLMs with preferences generated by a reward model, evaluating on two benchmarks (AlpacaEval 2.0 and Arena-Hard). Experimental results demonstrate that prompts with higher PVar outperform randomly selected prompts or those with lower PVar. We also show that our PVar-based selection method is robust, when using smaller reward models (1B, 3B) for selection. Notably, in a separate experiment using the original human annotations from the UltraFeedback dataset, we found that training on only the top 10\% of prompts with the highest PVar yields better evaluation performance than training on the full dataset, highlighting the importance of preference variance in identifying informative examples for efficient LLM alignment.

Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains. Recent research has increasingly focused on the role of token importance in improving DPO effectiveness. It is observed that identical or semantically similar content (defined as ambiguous content) frequently appears within the preference pairs. We hypothesize that the presence of ambiguous content during DPO training may introduce ambiguity, thereby limiting further improvements in alignment. Through mathematical analysis and proof-of-concept experiments, we reveal that ambiguous content may potentially introduce ambiguities, thereby degrading performance. To address this issue, we introduce Ambiguity Awareness Optimization (AAO), a simple yet effective approach that automatically re-weights ambiguous content to reduce ambiguities by calculating semantic similarity from preference pairs. Through extensive experiments, we demonstrate that AAO consistently and significantly surpasses state-of-the-art approaches in performance, without markedly increasing response length, across multiple model scales and widely adopted benchmark datasets, including AlpacaEval 2, MT-Bench, and Arena-Hard. Specifically, AAO outperforms DPO by up to 8.9 points on AlpacaEval 2 and achieves an improvement of by up to 15.0 points on Arena-Hard.

Reinforcement Learning (RL) has been shown to improve the capabilities of large language models (LLMs). However, applying RL to open-domain tasks faces two key challenges: (1) the inherent subjectivity of these tasks prevents the verifiable rewards as required by Reinforcement Learning with Verifiable Rewards (RLVR); (2) Reinforcement Learning from Human Feedback (RLHF) relies on external reward mechanisms. To overcome these limitations, we propose Self-Examining Reinforcement Learning (SERL), a novel self-improving framework where the LLM serves as both Actor and Judge. SERL introduces two synergistic reward mechanisms without any external signals. On the one hand, to improve the Actor's capability, we derive rewards from Copeland-style pairwise comparison judgments across a group of generated responses. On the other hand, a self-consistency reward that encourages coherent judgments is proposed to improve the Judge's reliability. This process refines the Judge's capability, which in turn provides a more robust reward for Actor. Experiments show that our method outperforms existing self-improvement training methods. SERL improves the LC win rate of Qwen3-8B on AlpacaEval 2 from 52.37% to 59.90%. To the best of our knowledge, our method achieves state-of-the-art performance among self-improving approaches. Furthermore, it achieves a performance comparable to significantly larger models like Qwen3-32B, demonstrating superior effectiveness and robustness on open-domain tasks.

Large models have achieved remarkable performance across a range of reasoning and understanding tasks. Prior work often utilizes model ensembles or multi-agent systems to collaboratively generate responses, effectively operating in a server-to-server paradigm. However, such approaches do not align well with practical deployment settings, where a limited number of server-side models are shared by many clients under modern internet architectures. In this paper, we introduce \textbf{CoLM} (\textbf{Co}llaboration in \textbf{L}arge-\textbf{M}odels), a novel framework for collaborative reasoning that redefines cooperation among large models from a client-server perspective. Unlike traditional ensemble methods that rely on simultaneous inference from multiple models to produce a single output, CoLM allows the outputs of multiple models to be aggregated or shared, enabling each client model to independently refine and update its own generation based on these high-quality outputs. This design enables collaborative benefits by fully leveraging both client-side and shared server-side models. We further extend CoLM to vision-language models (VLMs), demonstrating its applicability beyond language tasks. Experimental results across multiple benchmarks show that CoLM consistently improves model performance on previously failed queries, highlighting the effectiveness of collaborative guidance in enhancing single-model capabilities.

Large Language Models (LLMs) have demonstrated remarkable progress through preference-based fine-tuning, which critically depends on the quality of the underlying training data. While human feedback is essential for improving data quality, it is costly and does not scale well. In this paper, we introduce Refine-n-Judge, an automated iterative approach that leverages a single LLM as both a refiner and a judge to enhance dataset quality. Unlike existing iterative refinement methods, Refine-n-Judge employs an LLM to both generate refinements and explicitly evaluate each improvement, ensuring that every iteration meaningfully enhances the dataset without requiring additional human annotation or a separate reward model. At each step, the LLM refines a response and judges whether the refinement is an improvement over the previous answer. This process continues until the LLM prefers the initial answer over the refinement, indicating no further improvements. This produces sequences of increasing quality, preference-labeled responses ideal for fine-tuning. We demonstrate the effectiveness of Refine-n-Judge across a range of public datasets spanning five corpora, targeting tasks such as coding, math, and conversation. Models (Llama 3.1-8B and Llama 3.3-70B) fine-tuned on Refine-n-Judge-enhanced datasets were preferred by LLM judges in over 74% of comparisons against models tuned on the original dataset by GPT-4. Additionally, we report performance gains: +5% on AlpacaEval and AlpacaEval 2.0, and +19% on MT-Bench. Our results indicate that Refine-n-Judge produces high-quality datasets and scalable model improvements.

The alignment of Large Language Models (LLMs) is crucial for ensuring their safety and reliability in practical applications. Direct Preference Optimization (DPO) has emerged as an efficient method that directly optimizes models using preference pairs, significantly reducing resource demands. However, the effectiveness of DPO heavily depends on the data quality, which is frequently compromised by noise. In this work, we propose $γ$-PO, a dynamic target margin preference optimization algorithm that adjust reward margins at the pairwise level. By introducing instance-specific margin calibration, $γ$-PO strategically prioritizes high-confidence pairs (those demonstrating higher reward margins) while suppressing potential noise from ambiguous pairs. Moreover, $γ$-PO is a plug-and-play method, compatible with variants of DPO that rely on reward margin between preference pairs. Across benchmarks such as AlpacaEval2 and Arena-Hard, $γ$-PO achieves an average 4.4\% improvement over other baselines, setting new benchmarks for state-of-the-art performance. Additionally, $γ$-PO requires minimal code changes and has a negligible impact on training efficiency, making it a robust solution for enhancing LLMs alignment. Our codes are available at \href{https://github.com/sunjie279/gammaPO}{https://github.com/sunjie279/gammaPO}.