Hongxin Zhang


2023

pdf bib
On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Omar Shaikh | Hongxin Zhang | William Held | Michael Bernstein | Diyi Yang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Generating a Chain of Thought (CoT) has been shown to consistently improve large language model (LLM) performance on a wide range of NLP tasks. However, prior work has mainly focused on logical reasoning tasks (e.g. arithmetic, commonsense QA); it remains unclear whether improvements hold for more diverse types of reasoning, especially in socially situated contexts. Concretely, we perform a controlled evaluation of zero-shot CoT across two socially sensitive domains: harmful questions and stereotype benchmarks. We find that zero-shot CoT reasoning in sensitive domains significantly increases a model’s likelihood to produce harmful or undesirable output, with trends holding across different prompt formats and model variants. Furthermore, we show that harmful CoTs increase with model size, but decrease with improved instruction following. Our work suggests that zero-shot CoT should be used with caution on socially important tasks, especially when marginalized groups or sensitive topics are involved.

pdf bib
Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints
Albert Lu | Hongxin Zhang | Yanzhe Zhang | Xuezhi Wang | Diyi Yang
Findings of the Association for Computational Linguistics: EACL 2023

The limits of open-ended generative models are unclear, yet increasingly important. What causes them to succeed and what causes them to fail? In this paper, we take a prompt-centric approach to analyzing and bounding the abilities of open-ended generative models. We present a generic methodology of analysis with two challenging prompt constraint types: structural and stylistic. These constraint types are categorized into a set of well-defined constraints that are analyzable by a single prompt. We then systematically create a diverse set of simple, natural, and useful prompts to robustly analyze each individual constraint. Using the GPT-3 text-davinci-002 model as a case study, we generate outputs from our collection of prompts and analyze the model’s generative failures. We also show the generalizability of our proposed method on other large models like BLOOM and OPT. Our results and our in-context mitigation strategies reveal open challenges for future research.

pdf bib
Werewolf Among Us: Multimodal Resources for Modeling Persuasion Behaviors in Social Deduction Games
Bolin Lai | Hongxin Zhang | Miao Liu | Aryan Pariani | Fiona Ryan | Wenqi Jia | Shirley Anugrah Hayati | James Rehg | Diyi Yang
Findings of the Association for Computational Linguistics: ACL 2023

Persuasion modeling is a key building block for conversational agents. Existing works in this direction are limited to analyzing textual dialogue corpus. We argue that visual signals also play an important role in understanding human persuasive behaviors. In this paper, we introduce the first multimodal dataset for modeling persuasion behaviors. Our dataset includes 199 dialogue transcriptions and videos captured in a multi-player social deduction game setting, 26,647 utterance level annotations of persuasion strategy, and game level annotations of deduction game outcomes. We provide extensive experiments to show how dialogue context and visual signals benefit persuasion strategy prediction. We also explore the generalization ability of language models for persuasion modeling and the role of persuasion strategies in predicting social deduction game outcomes. Our dataset can be found at https://persuasion-deductiongame. socialai-data.org. The codes and models are available at https://github.com/SALT-NLP/PersuationGames.

2022

pdf bib
Robustness of Demonstration-based Learning Under Limited Data Scenario
Hongxin Zhang | Yanzhe Zhang | Ruiyi Zhang | Diyi Yang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Demonstration-based learning has shown great potential in stimulating pretrained language models’ ability under limited data scenario. Simply augmenting the input with some demonstrations can significantly improve performance on few-shot NER. However, why such demonstrations are beneficial for the learning process remains unclear since there is no explicit alignment between the demonstrations and the predictions. In this paper, we design pathological demonstrations by gradually removing intuitively useful information from the standard ones to take a deep dive of the robustness of demonstration-based sequence labeling and show that (1) demonstrations composed of random tokens still make the model a better few-shot learner; (2) the length of random demonstrations and the relevance of random tokens are the main factors affecting the performance; (3) demonstrations increase the confidence of model predictions on captured superficial patterns. We have publicly released our code at https://github.com/SALT-NLP/RobustDemo.