Weiyan Shi


2024

pdf bib
Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future
Minzhi Li | Weiyan Shi | Caleb Ziems | Diyi Yang
Findings of the Association for Computational Linguistics ACL 2024

As Natural Language Processing (NLP) systems become increasingly integrated into human social life, these technologies will need to increasingly rely on social intelligence. Although there are many valuable datasets that benchmark isolated dimensions of social intelligence, there does not yet exist any body of work to join these threads into a cohesive subfield in which researchers can quickly identify research gaps and future directions. Towards this goal, we build a Social AI Data Infrastructure, which consists of a comprehensive social AI taxonomy and a data library of 480 NLP datasets. Our infrastructure allows us to analyze existing dataset efforts, and also evaluate language models’ performance in different social intelligence aspects. Our analyses demonstrate its utility in enabling a thorough understanding of current data landscape and providing a holistic perspective on potential directions for future dataset development. We show there is a need for multifaceted datasets, increased diversity in language and culture, more long-tailed social situations, and more interactive data in future social intelligence data efforts.

pdf bib
When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels
Weiyan Shi | Emily Dinan | Kurt Shuster | Jason Weston | Jing Xu
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Deployed dialogue agents have the potential to integrate human feedback to continuously improve themselves. However, humans may not always provide explicit signals when the chatbot makes mistakes during interactions. In this work, we propose Juicer, a framework to make use of both binary and free-form textual human feedback. It works by: (i) extending sparse binary feedback by training a satisfaction classifier to label the unlabeled data; and (ii) training a reply corrector to map the bad replies to good ones. We find that augmenting training with model-corrected replies improves the final dialogue model, and we can further improve performance by using both positive and negative replies through the recently proposed Director model.

pdf bib
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
Yi Zeng | Hongpeng Lin | Jingwen Zhang | Diyi Yang | Ruoxi Jia | Weiyan Shi
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Most traditional AI safety research views models as machines and centers on algorithm-focused attacks developed by security experts. As large language models (LLMs) become increasingly common and competent, non-expert users can also impose risks during daily interactions. Observing this, we shift the perspective, by treating LLMs as human-like communicators to examine the interplay between everyday language interaction and AI safety. Specifically, we study how to persuade LLMs to jailbreak them. First, we propose a persuasion taxonomy derived from decades of social science research. Then, we apply the taxonomy to automatically generate persuasive adversarial prompts (PAP) to jailbreak LLMs. Results show that persuasion significantly increases the jailbreak risk across all risk categories: PAP consistently achieves an attack success rate of over 92% on Llama-2-7b-Chat, GPT-3.5, and GPT-4 in 10 trials, surpassing recent algorithm-focused attacks. On the defense side, we explore various mechanisms against PAP, find a significant gap in existing defenses, and advocate for more fundamental solutions for AI safety.

pdf bib
The Earth is Flat because...: Investigating LLMs’ Belief towards Misinformation via Persuasive Conversation
Rongwu Xu | Brian Lin | Shujian Yang | Tianqi Zhang | Weiyan Shi | Tianwei Zhang | Zhixuan Fang | Wei Xu | Han Qiu
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility behavior in a single-turn setting. However, belief can change during a multi-turn conversation, especially a persuasive one. Therefore, in this study, we delve into LLMs’ susceptibility to persuasive conversations, particularly on factual questions that they can answer correctly. We first curate the Farm (i.e., Fact to Misinform) dataset, which contains factual questions paired with systematically generated persuasive misinformation. Then, we develop a testing framework to track LLMs’ belief changes in a persuasive dialogue. Through extensive experiments, we find that LLMs’ correct beliefs on factual knowledge can be easily manipulated by various persuasive strategies.

2023

pdf bib
Controllable Mixed-Initiative Dialogue Generation through Prompting
Maximillian Chen | Xiao Yu | Weiyan Shi | Urvi Awasthi | Zhou Yu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner. The standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. However, these supervised generation models are limited by the cost and quality of data annotation. We instead prompt large language models as a drop-in replacement to fine-tuning on conditional generation. We formalize prompt construction for controllable mixed-initiative dialogue. Our findings show improvements over fine-tuning and ground truth responses according to human evaluation and automatic metrics for two tasks: PersuasionForGood and Emotional Support Conversations.

pdf bib
AutoReply: Detecting Nonsense in Dialogue with Discriminative Replies
Weiyan Shi | Emily Dinan | Adi Renduchintala | Daniel Fried | Athul Jacob | Zhou Yu | Mike Lewis
Findings of the Association for Computational Linguistics: EMNLP 2023

We show that dialogue models can detect errors in their own messages, by calculating the likelihood of replies that are indicative of poor messages. For example, if an agent believes its partner is likely to respond “I don’t understand” to a candidate message, that message may not make sense, so an alternative message should be chosen. We evaluate our approach on a dataset from the game Diplomacy, which contains long dialogues richly grounded in the game state, on which existing models make many errors. We first show that hand-crafted replies can be effective for the task of detecting nonsense in applications as complex as Diplomacy. We then design AutoReply, an algorithm to search for such discriminative replies automatically, given a small number of annotated dialogue examples. We find that AutoReply-generated replies outperform handcrafted replies and perform on par with supervised learning approaches.

pdf bib
Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks
Kushal Chawla | Weiyan Shi | Jingwen Zhang | Gale Lucas | Zhou Yu | Jonathan Gratch
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Dialogue systems capable of social influence such as persuasion, negotiation, and therapy, are essential for extending the use of technology to numerous realistic scenarios. However, existing research primarily focuses on either task-oriented or open-domain scenarios, a categorization that has been inadequate for capturing influence skills systematically. There exists no formal definition or category for dialogue systems with these skills and data-driven efforts in this direction are highly limited. In this work, we formally define and introduce the category of social influence dialogue systems that influence users’ cognitive and emotional responses, leading to changes in thoughts, opinions, and behaviors through natural conversations. We present a survey of various tasks, datasets, and methods, compiling the progress across seven diverse domains. We discuss the commonalities and differences between the examined systems, identify limitations, and recommend future directions. This study serves as a comprehensive reference for social influence dialogue systems to inspire more dedicated research and discussion in this emerging area.

pdf bib
Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)
Kushal Chawla | Weiyan Shi
Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)

2022

pdf bib
Selective Differential Privacy for Language Modeling
Weiyan Shi | Aiqi Cui | Evan Li | Ruoxi Jia | Zhou Yu
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this challenge by training RNN-based language models with differential privacy guarantees. However, applying classical differential privacy to language models leads to poor model performance as the underlying privacy notion is over-pessimistic and provides undifferentiated protection for all tokens in the data. Given that the private information in natural language is sparse (for example, the bulk of an email might not carry personally identifiable information), we propose a new privacy notion, selective differential privacy, to provide rigorous privacy guarantees on the sensitive portion of the data to improve model utility. To realize such a new notion, we develop a corresponding privacy mechanism, Selective-DPSGD, for RNN-based language models. Besides language modeling, we also apply the method to a more concrete application – dialog systems. Experiments on both language modeling and dialog system building show that the proposed privacy-preserving mechanism achieves better utilities while remaining safe under various privacy attacks compared to the baselines. The data and code are released at https://github.com/wyshi/lm_privacy to facilitate future research.

pdf bib
Towards Socially Intelligent Agents with Mental State Transition and Human Value
Liang Qiu | Yizhou Zhao | Yuan Liang | Pan Lu | Weiyan Shi | Zhou Yu | Song-Chun Zhu
Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue

Building a socially intelligent agent involves many challenges. One of which is to track the agent’s mental state transition and teach the agent to make decisions guided by its value like a human. Towards this end, we propose to incorporate mental state simulation and value modeling into dialogue agents. First, we build a hybrid mental state parser that extracts information from both the dialogue and event observations and maintains a graphical representation of the agent’s mind; Meanwhile, the transformer-based value model learns human preferences from the human value dataset, ValueNet. Empirical results show that the proposed model attains state-of-the-art performance on the dialogue/action/emotion prediction task in the fantasy text-adventure game dataset, LIGHT. We also show example cases to demonstrate: (i) how the proposed mental state parser can assist the agent’s decision by grounding on the context like locations and objects, and (ii) how the value model can help the agent make decisions based on its personal priorities.

pdf bib
Just Fine-tune Twice: Selective Differential Privacy for Large Language Models
Weiyan Shi | Ryan Shea | Si Chen | Chiyuan Zhang | Ruoxi Jia | Zhou Yu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Protecting large language models from privacy leakage is becoming increasingly crucial with their wide adoption in real-world products. Yet applying *differential privacy* (DP), a canonical notion with provable privacy guarantees for machine learning models, to those models remains challenging due to the trade-off between model utility and privacy loss. Utilizing the fact that sensitive information in language data tends to be sparse, Shi et al. (2021) formalized a DP notion extension called *Selective Differential Privacy* (SDP) to protect only the sensitive tokens defined by a policy function. However, their algorithm only works for RNN-based models. In this paper, we develop a novel framework, *Just Fine-tune Twice* (JFT), that achieves SDP for state-of-the-art large transformer-based models. Our method is easy to implement: it first fine-tunes the model with *redacted* in-domain data, and then fine-tunes it again with the *original* in-domain data using a private training mechanism. Furthermore, we study the scenario of imperfect implementation of policy functions that misses sensitive tokens and develop systematic methods to handle it. Experiments show that our method achieves strong utility compared to previous baselines. We also analyze the SDP privacy guarantee empirically with the canary insertion attack.

pdf bib
Proceedings of the 4th Workshop on NLP for Conversational AI
Bing Liu | Alexandros Papangelis | Stefan Ultes | Abhinav Rastogi | Yun-Nung Chen | Georgios Spithourakis | Elnaz Nouri | Weiyan Shi
Proceedings of the 4th Workshop on NLP for Conversational AI

pdf bib
Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue
Maximillian Chen | Weiyan Shi | Feifan Yan | Ryan Hou | Jingwen Zhang | Saurav Sahay | Zhou Yu
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Complex conversation settings such as persuasion involve communicating changes in attitude or behavior, so users’ perspectives need to be addressed, even when not directly related to the topic. In this work, we contribute a novel modular dialogue system framework that seamlessly integrates factual information and social content into persuasive dialogue. Our framework is generalizable to any dialogue tasks that have mixed social and task contents. We conducted a study that compared user evaluations of our framework versus a baseline end-to-end generation model. We found our model was evaluated to be more favorable in all dimensions including competence and friendliness compared to the baseline model which does not explicitly handle social content or factual questions.

2021

pdf bib
PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation
Jing Gu | Qingyang Wu | Chongruo Wu | Weiyan Shi | Zhou Yu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Large pre-trained language generation models such as GPT-2 have demonstrated their effectiveness as language priors by reaching state-of-the-art results in various language generation tasks. However, the performance of pre-trained models on task-oriented dialog tasks is still under-explored. We propose a Pre-trainedRole Alternating Language model (PRAL), explicitly designed for task-oriented conversational systems. We design several techniques: start position randomization, knowledge distillation, and history discount to improve pre-training performance. In addition, we introduce a high-quality large-scale task-oriented dialog pre-training dataset by post-prossessing13 dialog datasets. We effectively adapt PRALon three downstream tasks. The results show that PRAL outperforms or is on par with state-of-the-art models.

pdf bib
LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing
Yu Li | Josh Arnold | Feifan Yan | Weiyan Shi | Zhou Yu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations

We present LEGOEval, an open-source toolkit that enables researchers to easily evaluate dialogue systems in a few lines of code using the online crowdsource platform, Amazon Mechanical Turk. Compared to existing toolkits, LEGOEval features a flexible task design by providing a Python API that maps to commonly used React.js interface components. Researchers can personalize their evaluation procedures easily with our built-in pages as if playing with LEGO blocks. Thus, LEGOEval provides a fast, consistent method for reproducing human evaluation results. Besides the flexible task design, LEGOEval also offers an easy API to review collected data.

pdf bib
Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration
Weiyan Shi | Yu Li | Saurav Sahay | Zhou Yu
Findings of the Association for Computational Linguistics: EMNLP 2021

Persuasion dialogue system reflects the machine’s ability to make strategic moves beyond verbal communication, and therefore differentiates itself from task-oriented or open-domain dialogues and has its own unique values. However, the repetition and inconsistency problems still persist in dialogue response generation and could substantially impact user experience and impede the persuasion outcome. Besides, although reinforcement learning (RL) approaches have achieved big success in strategic tasks such as games, it requires a sophisticated user simulator to provide real-time feedback to the dialogue system, which limits the application of RL on persuasion dialogues. To address these issues towards a better persuasion dialogue system, we apply RL to refine a language model baseline without user simulators, and distill sentence-level information about repetition, inconsistency, and task relevance through rewards. Moreover, to better accomplish the persuasion task, the model learns from human demonstration to imitate human persuasion behavior and selects the most persuasive responses. Experiments show that our model outperforms previous state-of-the-art dialogue models on both automatic metrics and human evaluation results on a donation persuasion task, and generates more diverse, consistent and persuasive conversations according to the user feedback. We will make the code and model publicly available.

2020

pdf bib
Understanding User Resistance Strategies in Persuasive Conversations
Youzhi Tian | Weiyan Shi | Chen Li | Zhou Yu
Findings of the Association for Computational Linguistics: EMNLP 2020

Persuasive dialog systems have various usages, such as donation persuasion and physical exercise persuasion. Previous persuasive dialog systems research mostly focused on analyzing the persuader’s strategies and paid little attention to the persuadee (user). However, understanding and addressing users’ resistance strategies is an essential job of a persuasive dialog system. So, we adopt a preliminary framework on persuasion resistance in psychology and design a fine-grained resistance strategy annotation scheme. We annotate the PersuasionForGood dataset with the scheme. With the enriched annotations, we build a classifier to predict the resistance strategies. Furthermore, we analyze the relationships between persuasion strategies and persuasion resistance strategies. Our work lays the ground for developing a persuasive dialogue system that can understand and address user resistance strategy appropriately. The code and data will be released.

pdf bib
Structured Attention for Unsupervised Dialogue Structure Induction
Liang Qiu | Yizhou Zhao | Weiyan Shi | Yuan Liang | Feng Shi | Tao Yuan | Zhou Yu | Song-Chun Zhu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Inducing a meaningful structural representation from one or a set of dialogues is a crucial but challenging task in computational linguistics. Advancement made in this area is critical for dialogue system design and discourse analysis. It can also be extended to solve grammatical inference. In this work, we propose to incorporate structured attention layers into a Variational Recurrent Neural Network (VRNN) model with discrete latent states to learn dialogue structure in an unsupervised fashion. Compared to a vanilla VRNN, structured attention enables a model to focus on different parts of the source sentence embeddings while enforcing a structural inductive bias. Experiments show that on two-party dialogue datasets, VRNN with structured attention learns semantic structures that are similar to templates used to generate this dialogue corpus. While on multi-party dialogue datasets, our model learns an interactive structure demonstrating its capability of distinguishing speakers or addresses, automatically disentangling dialogues without explicit human annotation.

pdf bib
INSPIRED: Toward Sociable Recommendation Dialog Systems
Shirley Anugrah Hayati | Dongyeop Kang | Qingxiaoyang Zhu | Weiyan Shi | Zhou Yu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In recommendation dialogs, humans commonly disclose their preference and make recommendations in a friendly manner. However, this is a challenge when developing a sociable recommendation dialog system, due to the lack of dialog dataset annotated with such sociable strategies. Therefore, we present INSPIRED, a new dataset of 1,001 human-human dialogs for movie recommendation with measures for successful recommendations. To better understand how humans make recommendations in communication, we design an annotation scheme related to recommendation strategies based on social science theories and annotate these dialogs. Our analysis shows that sociable recommendation strategies, such as sharing personal opinions or communicating with encouragement, more frequently lead to successful recommendations. Based on our dataset, we train end-to-end recommendation dialog systems with and without our strategy labels. In both automatic and human evaluation, our model with strategy incorporation outperforms the baseline model. This work is a first step for building sociable recommendation dialog systems with a basis of social science theories.

2019

pdf bib
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
Xuewei Wang | Weiyan Shi | Richard Kim | Yoojung Oh | Sijia Yang | Jingwen Zhang | Zhou Yu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Developing intelligent persuasive conversational agents to change people’s opinions and actions for social good is the frontier in advancing the ethical development of automated dialogue systems. To do so, the first step is to understand the intricate organization of strategic disclosures and appeals employed in human persuasion conversations. We designed an online persuasion task where one participant was asked to persuade the other to donate to a specific charity. We collected a large dataset with 1,017 dialogues and annotated emerging persuasion strategies from a subset. Based on the annotation, we built a baseline classifier with context information and sentence-level features to predict the 10 persuasion strategies used in the corpus. Furthermore, to develop an understanding of personalized persuasion processes, we analyzed the relationships between individuals’ demographic and psychological backgrounds including personality, morality, value systems, and their willingness for donation. Then, we analyzed which types of persuasion strategies led to a greater amount of donation depending on the individuals’ personal backgrounds. This work lays the ground for developing a personalized persuasive dialogue system.

pdf bib
Unsupervised Dialog Structure Learning
Weiyan Shi | Tiancheng Zhao | Zhou Yu
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Learning a shared dialog structure from a set of task-oriented dialogs is an important challenge in computational linguistics. The learned dialog structure can shed light on how to analyze human dialogs, and more importantly contribute to the design and evaluation of dialog systems. We propose to extract dialog structures using a modified VRNN model with discrete latent vectors. Different from existing HMM-based models, our model is based on variational-autoencoder (VAE). Such model is able to capture more dynamics in dialogs beyond the surface forms of the language. We find that qualitatively, our method extracts meaningful dialog structure, and quantitatively, outperforms previous models on the ability to predict unseen data. We further evaluate the model’s effectiveness in a downstream task, the dialog system building task. Experiments show that, by integrating the learned dialog structure into the reward function design, the model converges faster and to a better outcome in a reinforcement learning setting.

pdf bib
How to Build User Simulators to Train RL-based Dialog Systems
Weiyan Shi | Kun Qian | Xuewei Wang | Zhou Yu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

User simulators are essential for training reinforcement learning (RL) based dialog models. The performance of the simulator directly impacts the RL policy. However, building a good user simulator that models real user behaviors is challenging. We propose a method of standardizing user simulator building that can be used by the community to compare dialog system quality using the same set of user simulators fairly. We present implementations of six user simulators trained with different dialog planning and generation methods. We then calculate a set of automatic metrics to evaluate the quality of these simulators both directly and indirectly. We also ask human users to assess the simulators directly and indirectly by rating the simulated dialogs and interacting with the trained systems. This paper presents a comprehensive evaluation framework for user simulator study and provides a better understanding of the pros and cons of different user simulators, as well as their impacts on the trained systems.

2018

pdf bib
Sentiment Adaptive End-to-End Dialog Systems
Weiyan Shi | Zhou Yu
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

End-to-end learning framework is useful for building dialog systems for its simplicity in training and efficiency in model updating. However, current end-to-end approaches only consider user semantic inputs in learning and under-utilize other user information. Therefore, we propose to include user sentiment obtained through multimodal information (acoustic, dialogic and textual), in the end-to-end learning framework to make systems more user-adaptive and effective. We incorporated user sentiment information in both supervised and reinforcement learning settings. In both settings, adding sentiment information reduced the dialog length and improved the task success rate on a bus information search task. This work is the first attempt to incorporate multimodal user information in the adaptive end-to-end dialog system training framework and attained state-of-the-art performance.

pdf bib
Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization
Jilei Wang | Shiying Luo | Weiyan Shi | Tao Dai | Shu-Tao Xia
Proceedings of the Third Workshop on Representation Learning for NLP

Learning vector space representation of words (i.e., word embeddings) has recently attracted wide research interests, and has been extended to cross-lingual scenario. Currently most cross-lingual word embedding learning models are based on sentence alignment, which inevitably introduces much noise. In this paper, we show in Chinese and Japanese, the acquisition of semantic relation among words can benefit from the large number of common characters shared by both languages; inspired by this unique feature, we design a method named CJC targeting to generate cross-lingual context of words. We combine CJC with GloVe based on matrix factorization, and then propose an integrated model named CJ-Glo. Taking two sentence-aligned models and CJ-BOC (also exploits common characters but is based on CBOW) as baseline algorithms, we compare them with CJ-Glo on a series of NLP tasks including cross-lingual synonym, word analogy and sentence alignment. The result indicates CJ-Glo achieves the best performance among these methods, and is more stable in cross-lingual tasks; moreover, compared with CJ-BOC, CJ-Glo is less sensitive to the alteration of parameters.