Author name cluster

Geyang Guo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

ICLR Conference 2025 Conference Paper

Preference Optimization for Reasoning with Pseudo Feedback

Fangkai Jiao
Geyang Guo
Xingxing Zhang
Nancy F. Chen
Shafiq Joty
Furu Wei

Preference optimization techniques, such as Direct Preference Optimization (DPO), are frequently employed to enhance the reasoning capabilities of large language models (LLMs) in domains like mathematical reasoning and coding, typically following supervised fine-tuning. These methods rely on high-quality labels for reasoning tasks to generate preference pairs; however, the availability of reasoning datasets with human-verified labels is limited. In this study, we introduce a novel approach to generate pseudo feedback for reasoning tasks by framing the labeling of solutions to reason problems as an evaluation against associated \emph{test cases}. We explore two forms of pseudo feedback based on test cases: one generated by frontier LLMs and the other by extending self-consistency to multi-test-case. We conduct experiments on both mathematical reasoning and coding tasks using pseudo feedback for preference optimization, and observe improvements across both tasks. Specifically, using Mathstral-7B as our base model, we improve MATH results from 58.3 to 68.6, surpassing both NuminaMath-72B and GPT-4-Turbo-1106-preview. In GSM8K and College Math, our scores increase from 85.6 to 90.3 and from 34.3 to 42.3, respectively. Building on Deepseek-coder-7B-v1.5, we achieve a score of 24.3 on LiveCodeBench (from 21.1), surpassing Claude-3-Haiku.

Details

ICLR Conference 2024 Conference Paper

Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment

Geyang Guo
Ranchi Zhao
Tianyi Tang
Xin Zhao 0018
Ji-Rong Wen

Alignment with human preference is a desired property of large language models (LLMs). Currently, the main alignment approach is based on reinforcement learning from human feedback (RLHF). Despite the effectiveness of RLHF, it is intricate to implement and train, thus recent studies explore how to develop alternative alignment approaches based on supervised fine-tuning (SFT). A major limitation of SFT is that it essentially does imitation learning, which can't fully understand what are the expected behaviors. To address this issue, we propose an improved alignment approach named $\textbf{FIGA}$. Different from prior methods, we incorporate fine-grained (i.e., token or phrase level) quality signals that are derived by contrasting good and bad responses. Our approach has made two major contributions. Firstly, we curate a refined alignment dataset that pairs initial responses and the corresponding revised ones. Secondly, we devise a new loss function can leverage fine-grained quailty signals to instruct the learning of LLMs for alignment. Extensive experiments have demonstrated the effectiveness of our approaches by comparing a number of competitive baselines.

Details

NeurIPS Conference 2024 Conference Paper

S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity

Xinyu Yang
Jixuan Leng
Geyang Guo
Jiawei Zhao
Ryumei Nakada
Linjun Zhang
Huaxiu Yao
Beidi Chen

Current PEFT methods for LLMs can achieve high quality, efficient training, or scalable serving, but not all three simultaneously. To address this limitation, we investigate sparse fine-tuning and observe a remarkable improvement in generalization ability. Utilizing this key insight, we propose a family of Structured Sparse Fine-Tuning (S${^2}$FT) methods for LLMs, which concurrently achieve state-of-the-art fine-tuning performance, training efficiency, and inference scalability. S${^2}$FT accomplishes this by "selecting sparsely and computing densely". Based on the coupled structures in LLMs, \model selects a few attention heads and channels in the MHA and FFN modules for each Transformer block, respectively. Next, it co-permutes the weight matrices on both sides of all coupled structures to connect the selected subsets in each layer into a dense submatrix. Finally, S${^2}$FT performs in-place gradient updates on all selected submatrices. Through theoretical analyses and empirical results, our method prevents forgetting while simplifying optimization, delivers SOTA performance on both commonsense and arithmetic reasoning with 4. 6% and 1. 3% average improvements compared to LoRA, and surpasses full FT by 11. 5% when generalizing to various domains after instruction tuning. Using our partial back-propagation algorithm, S${^2}$FT saves training memory up to 3$\times$ and improves latency by 1. 5-2. 7$\times$ compared to full FT, while achieving an average 10\% improvement over LoRA on both metrics. We further demonstrate that the weight updates in S${^2}$FT can be decoupled into adapters, enabling effective fusion, fast switch, and efficient parallelism when serving multiple fine-tuned models.

PDF Details DOI