Related papers: Optimizing Prompts for Large Language Models: A Ca…
Recent advances in large language models (LLMs) have greatly improved their reasoning and decision-making abilities when deployed as agents. Richer reasoning, however, often comes at the cost of longer chain of thought (CoT), hampering…
Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…
Direct Preference Optimization (DPO) have emerged as a popular method for aligning Large Language Models (LLMs) with human preferences. While DPO effectively preserves the relative ordering between chosen and rejected responses through…
Large language models (LLMs) typically operate in a question-answering paradigm, where the quality of the input prompt critically affects the response. Automated Prompt Optimization (APO) aims to overcome the cognitive biases of manually…
Large language models (LLMs) have achieved impressive results on complex reasoning tasks, but their high inference cost remains a major barrier to real-world deployment. A promising solution is to use cascaded inference, where small, cheap…
Prompting is fundamental to unlocking the full potential of large language models. To automate and enhance this process, automatic prompt optimization (APO) has been developed, demonstrating effectiveness primarily in text-only input…
Direct Preference Optimization (DPO) using an implicit reward model has proven to be an effective alternative to reinforcement learning from human feedback (RLHF) for fine-tuning preference aligned large language models (LLMs). However, the…
Mathematical reasoning is a crucial capability for Large Language Models (LLMs), yet generating detailed and accurate reasoning traces remains a significant challenge. This paper introduces a novel approach to produce high-quality reasoning…
Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, and produce verbose, repetitive prompts. We introduce PrefPO,…
Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, and LLM-based agents further extend these abilities to various practical workflows. While recent progress shows that multi-agent systems (MAS) can…
Numerous recent works aim to enhance the efficacy of Large Language Models (LLMs) through strategic prompting. In particular, the Optimization by PROmpting (OPRO) approach provides state-of-the-art performance by leveraging LLMs as…
Mathematical reasoning presents a significant challenge for Large Language Models (LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring the correctness of each reasoning step is critical. To address…
While prompt optimization has emerged as a critical technique for enhancing language model performance, existing approaches primarily focus on elicitation-based strategies that search for optimal prompts to activate models' capabilities.…
Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the need for reward models. However, due to the presence of…
We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward…
In the domain of complex reasoning tasks, such as mathematical reasoning, recent advancements have proposed the use of Direct Preference Optimization (DPO) to suppress output of dispreferred responses, thereby enhancing the long-chain…
Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated…
Large language models (LLMs) achieve strong performance across a wide range of tasks but are highly sensitive to prompt design, motivating the need for automatic prompt optimization. Existing methods predominantly focus on performance…
Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based prompt optimizers often…
Direct Preference Optimization (DPO) has proven effective at improving the performance of large language models (LLMs) on downstream tasks such as reasoning and alignment. In this work, we propose Step-Controlled DPO (SCDPO), a method for…