Quan Tu


2024

pdf bib
360∘REA: Towards A Reusable Experience Accumulation with 360∘ Assessment for Multi-Agent System
Shen Gao | Hao Li | Zhengliang Shi | Chengrui Huang | Quan Tu | Shuo Shang | Zhiliang Tian | Minlie Huang
Findings of the Association for Computational Linguistics ACL 2024

Large language model agents have demonstrated remarkable advancements across various complex tasks. Recent works focus on optimizing the agent team or employing self-reflection to iteratively solve complex tasks. Since these agents are all based on the same LLM, only conducting self-evaluation or removing underperforming agents does not substantively enhance the capability of the agents. We argue that a comprehensive evaluation and accumulating experience from evaluation feedback is an effective approach to improving system performance. In this paper, we propose Reusable Experience Accumulation with 360∘ Assessment (360∘REA), a hierarchical multi-agent framework inspired by corporate organizational practices. The framework employs a novel 360∘ performance assessment method for multi-perspective performance evaluation with fine-grained assessment. To enhance the capability of agents in addressing complex tasks, we introduce dual-level experience pool for agents to accumulate experience through fine-grained assessment. Extensive experiments on complex task datasets demonstrate the effectiveness of 360∘REA.

pdf bib
CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment
Jixiang Hong | Quan Tu | Changyu Chen | Gao Xing | Ji Zhang | Rui Yan
Findings of the Association for Computational Linguistics ACL 2024

Language models trained on large-scale corpus often generate harmful responses that are harmful and contrary to human values. A prevalent approach for human alignment is reinforcement learning from human feedback (RLHF), utilizing algorithms such as proximal policy optimization (PPO). However, these methods are often characterized by complexity, instability, and substantial resource consumption. Considering that existing large language models (LLMs) like ChatGPT are already relatively well-aligned and cost-friendly, researchers propose to align the language model with human preferences from AI feedback. Nevertheless, the common practices, that unidirectionally distill the responses, are constrained by the inherent capability of LLMs. To address it, we introduce CycleAlign, a framework that distills alignment capabilities from the parameter-invisible LLMs (black-box) to the parameter-visible models (white-box) in an iterative manner. CycleAlign iteratively improves both the white-box and black-box models by integrating static and dynamic in-context learning and a belief alignment method.Empirical results illustrate that the model fine-tuned by CycleAlign remarkably exceeds existing methods, and achieves the state-of-the-art performance in alignment with human value.

pdf bib
InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
Xintao Wang | Yunze Xiao | Jen-tse Huang | Siyu Yuan | Rui Xu | Haoran Guo | Quan Tu | Yaying Fei | Ziang Leng | Wei Wang | Jiangjie Chen | Cheng Li | Yanghua Xiao
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Role-playing agents (RPAs), powered by large language models, have emerged as a flourishing field of applications. However, a key challenge lies in assessing whether RPAs accurately reproduce the personas of target characters, namely their character fidelity. Existing methods mainly focus on the knowledge and linguistic patterns of characters. This paper, instead, introduces a novel perspective to evaluate the personality fidelity of RPAs with psychological scales. Overcoming drawbacks of previous self-report assessments on RPAs, we propose InCharacter, namely **In**terviewing **Character** agents for personality tests. Experiments include various types of RPAs and LLMs, covering 32 distinct characters on 14 widely used psychological scales. The results validate the effectiveness of InCharacter in measuring RPA personalities. Then, with InCharacter, we show that state-of-the-art RPAs exhibit personalities highly aligned with the human-perceived personalities of the characters, achieving an accuracy up to 80.7%.

pdf bib
CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation
Quan Tu | Shilong Fan | Zihang Tian | Tianhao Shen | Shuo Shang | Xin Gao | Rui Yan
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recently, the advent of large language models (LLMs) has revolutionized generative agents. Among them, Role-Playing Conversational Agents (RPCAs) attract considerable attention due to their ability to emotionally engage users. However, the absence of a comprehensive benchmark impedes progress in this field. To bridge this gap, we introduce CharacterEval, a Chinese benchmark for comprehensive RPCA assessment, complemented by a tailored high-quality dataset. The dataset comprises 1,785 multi-turn role-playing dialogues, encompassing 11,376 examples and featuring 77 characters derived from Chinese novels and scripts. It was carefully constructed, beginning with initial dialogue extraction via GPT-4, followed by rigorous human-led quality control, and enhanced with in-depth character profiles sourced from Baidu Baike. CharacterEval employs a multifaceted evaluation approach, encompassing thirteen targeted metrics on four dimensions. To facilitate the convenient evaluation for these subjective metrics in CharacterEval, we further developed CharacterRM, a role-playing reward model based on human annotations, which has a higher correlation with human judgment compared to GPT-4. Comprehensive experiments on CharacterEval demonstrate that Chinese LLMs exhibit more promising capabilities than GPT-4 in Chinese role-playing conversation.

pdf bib
Multi-Grained Conversational Graph Network for Retrieval-based Dialogue Systems
Quan Tu | Chongyang Tao | Rui Yan
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Retrieval-based dialogue agents aim at selecting a proper response according to multi-turn conversational history. Existing methods have achieved great progress in terms of retrieval accuracy on benchmarks with pre-trained language models. However, these methods simply concatenate all turns in the dialogue history as the input, ignoring the dialogue dependency and structural information between the utterances. Besides, they usually reason the relationship of the context-response pair at a single level of abstraction (e.g., utterance level), which can not comprehensively capture the fine-grained relation between the context and response. In this paper, we present the multi-grained conversational graph network (MCGN) that considers multiple levels of abstraction from dialogue histories and semantic dependencies within multi-turn dialogues for addressing. Evaluation results on two benchmarks indicate that the proposed multi-grained conversational graph network is helpful for dialogue context understanding and can bring consistent and significant improvement over the state-of-the-art methods.

2023

pdf bib
SSP: Self-Supervised Post-training for Conversational Search
Quan Tu | Shen Gao | Xiaolong Wu | Zhao Cao | Ji-Rong Wen | Rui Yan
Findings of the Association for Computational Linguistics: ACL 2023

Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which usually initialize parameters by query reformulation to discover contextualized dependency, have trouble in understanding the dialogue structure information and struggle with contextual semantic vanishing. In this paper, we propose {pasted macro ‘FULLMODEL’} ({pasted macro ‘MODEL’}) which is a new post-training paradigm with three self-supervised tasks to efficiently initialize the conversational search model to enhance the dialogue structure and contextual semantic understanding. Furthermore, the {pasted macro ‘MODEL’} can be plugged into most of the existing conversational models to boost their performance. To verify the effectiveness of our proposed method, we apply the conversational encoder post-trained by {pasted macro ‘MODEL’} on the conversational search task using two benchmark datasets: CAsT-19 and CAsT-20.Extensive experiments that our {pasted macro ‘MODEL’} can boost the performance of several existing conversational search methods. Our source code is available at https://github.com/morecry/SSP.

2022

pdf bib
MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation
Quan Tu | Yanran Li | Jianwei Cui | Bin Wang | Ji-Rong Wen | Rui Yan
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Applying existing methods to emotional support conversation—which provides valuable assistance to people who are in need—has two major limitations: (a) they generally employ a conversation-level emotion label, which is too coarse-grained to capture user’s instant mental state; (b) most of them focus on expressing empathy in the response(s) rather than gradually reducing user’s distress. To address the problems, we propose a novel model MISC, which firstly infers the user’s fine-grained emotional status, and then responds skillfully using a mixture of strategy. Experimental results on the benchmark dataset demonstrate the effectiveness of our method and reveal the benefits of fine-grained emotion understanding as well as mixed-up strategy modeling.