Cunhang Fan


2024

pdf bib
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models
Zhanyue Qin | Haochuan Wang | Deyuan Liu | Ziyang Song | Cunhang Fan | Zhao Lv | Jinlin Wu | Zhen Lei | Zhiying Tu | Dianhui Chu | Xiaoyan Yu | Dianbo Sui
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Sequential decision-making refers to algorithms that take into account the dynamics of the environment, where early decisions affect subsequent decisions. With large language models (LLMs) demonstrating powerful capabilities between tasks, we can’t help but ask: Can Current LLMs Effectively Make Sequential Decisions? In order to answer this question, we propose the UNO Arena based on the card game UNO to evaluate the sequential decision-making capability of LLMs and explain in detail why we choose UNO. In UNO Arena, We evaluate the sequential decision-making capability of LLMs dynamically with novel metrics based Monte Carlo methods. We set up random players, DQN-based reinforcement learning players, and LLM players (e.g. GPT-4, Gemini-pro) for comparison testing. Furthermore, in order to improve the sequential decision-making capability of LLMs, we propose the TUTRI player, which can involves having LLMs reflect their own actions with the summary of game history and the game strategy. Numerous experiments demonstrate that the TUTRI player achieves a notable breakthrough in the performance of sequential decision-making compared to the vanilla LLM player.

pdf bib
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
Deyuan Liu | Zhanyue Qin | Hairu Wang | Zhao Yang | Zecheng Wang | Fangying Rong | Qingbin Liu | Yanchao Hao | Bo Li | Xi Chen | Cunhang Fan | Zhao Lv | Dianhui Chu | Zhiying Tu | Dianbo Sui
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

While large language models (LLMs) excel in many domains, their complexity and scale challenge deployment in resource-limited environments. Current compression techniques, such as parameter pruning, often fail to effectively utilize the knowledge from pruned parameters. To address these challenges, we propose Manifold-Based Knowledge Alignment and Layer Merging Compression (MKA), a novel approach that uses manifold learning and the Information Bottleneck (IB) measure to merge similar layers, reducing model size while preserving essential performance. We evaluate MKA on multiple benchmark datasets and various LLMs. Our findings show that MKA not only preserves model performance but also achieves substantial compression ratios, outperforming traditional pruning methods. Moreover, when coupled with quantization, MKA delivers even greater compression. Specifically, on the MMLU dataset using the Llama3-8B model, MKA achieves a compression ratio of 43.75% with a minimal performance decrease of only 2.82%. The proposed MKA method offers a resource-efficient and performance-preserving model compression technique for LLMs. We make our code available at https://github.com/SempraETY/Pruning-via-Merging

pdf bib
Bilateral Masking with prompt for Knowledge Graph Completion
Yonghui Kong | Cunhang Fan | Yujie Chen | Shuai Zhang | Zhao Lv | Jianhua Tao
Findings of the Association for Computational Linguistics: NAACL 2024

The pre-trained language model (PLM) has achieved significant success in the field of knowledge graph completion (KGC) by effectively modeling entity and relation descriptions. In recent studies, the research in this field has been categorized into methods based on word matching and sentence matching, with the former significantly lags behind. However, there is a critical issue in word matching methods, which is that these methods fail to obtain satisfactory single embedding representations for entities.To address this issue and enhance entity representation, we propose the Bilateral Masking with prompt for Knowledge Graph Completion (BMKGC) approach.Our methodology employs prompts to narrow the distance between the predicted entity and the known entity. Additionally, the BMKGC model incorporates a bi-encoder architecture, enabling simultaneous predictions at both the head and tail. Furthermore, we propose a straightforward technique to augment positive samples, mitigating the problem of degree bias present in knowledge graphs and thereby improving the model’s robustness. Experimental results conclusively demonstrate that BMKGC achieves state-of-the-art performance on the WN18RR dataset.