As generative language models advance, users have started to utilize Large Language Models (LLMs) to assist in writing various types of content, including professional documents such as recommendation letters. Despite their convenience, these applications introduce unprecedented fairness concerns. As generated reference letters might be directly utilized by users in professional or academic scenarios, they have the potential to cause direct social harms, such as lowering success rates for female applicants. Therefore, it is imminent and necessary to comprehensively study fairness issues and associated harms in such real-world use cases for future mitigation and monitoring. In this paper, we critically examine gender bias in LLM-generated reference letters. Inspired by findings in social science, we design evaluation methods to manifest gender biases in LLM-generated letters through 2 dimensions: biases in language style and biases in lexical content. Furthermore, we investigate the extent of bias propagation by separately analyze bias amplification in model-hallucinated contents, which we define to be the hallucination bias of model-generated documents. Through benchmarking evaluation on 4 popular LLMs, including ChatGPT, Alpaca, Vicuna and StableLM, our study reveals significant gender biases in LLM-generated recommendation letters. Our findings further point towards the importance and imminence to recognize biases in LLM-generated professional documents.
Models of various NLP tasks have been shown to exhibit stereotypes, and the bias in the question answering (QA) models is especially harmful as the output answers might be directly consumed by the end users. There have been datasets to evaluate bias in QA models, while bias mitigation technique for the QA models is still under-explored. In this work, we propose BMBI, an approach to mitigate the bias of multiple-choice QA models. Based on the intuition that a model would lean to be more biased if it learns from a biased example, we measure the bias level of a query instance by observing its influence on another instance. If the influenced instance is more biased, we derive that the query instance is biased. We then use the bias level detected as an optimization objective to form a multi-task learning setting in addition to the original QA task. We further introduce a new bias evaluation metric to quantify bias in a comprehensive and sensitive way. We show that our method could be applied to multiple QA formulations across multiple bias categories. It can significantly reduce the bias level in all 9 bias categories in the BBQ dataset while maintaining comparable QA accuracy.
Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. Generic personas refer to an individual from a demographic group (e.g. an Asian person), whereas specific personas can be actual names of historical figures. While the adoption of personas allows dialogue systems to be more engaging and approachable to users, it also carries the potential risk of exacerbating social biases in model responses, further causing societal harms through interactions with users. In this paper, we systematically study "persona biases", which we define to be the sensitivity of harmful dialogue model behaviors to different persona adoptions. We categorize persona biases into biases in harmful expression and harmful agreement, as well as establish a comprehensive evaluation framework to measure persona biases in five aspects: Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic Agreement. Additionally, we propose to comprehensively investigate persona biases through experimenting with UniversalPersona, a systematized persona dataset with a comprehensive list of both generic and specific model personas. Through benchmarking on four different models, including Blender, ChatGPT, Alpaca, and Vicuna, our study uncovers significant persona biases in these dialogue systems.Findings of our study underscores the immediate need to revisit the use of persona traits in dialogue agents, to ensure their safe application.
Keyphrase Generation (KPG) is a longstanding task in NLP with widespread applications. The advent of sequence-to-sequence (seq2seq) pre-trained language models (PLMs) has ushered in a transformative era for KPG, yielding promising performance improvements. However, many design decisions remain unexplored and are often made arbitrarily. This paper undertakes a systematic analysis of the influence of model selection and decoding strategies on PLM-based KPG. We begin by elucidating why seq2seq PLMs are apt for KPG, anchored by an attention-driven hypothesis. We then establish that conventional wisdom for selecting seq2seq PLMs lacks depth: (1) merely increasing model size or performing task-specific adaptation is not parameter-efficient; (2) although combining in-domain pre-training with task adaptation benefits KPG, it does partially hinder generalization. Regarding decoding, we demonstrate that while greedy search delivers strong F1 scores, it lags in recall compared with sampling-based methods. From our insights, we propose DeSel, a likelihood-based decode-select algorithm that improves greedy search by an average of 4.7% semantic F1 across five datasets. Our collective findings pave the way for deeper future investigations into PLM-based KPG.
Prompting and adapter tuning have emerged as efficient alternatives to fine-tuning (FT) methods. However, existing studies on speech prompting focused on classification tasks and failed on more complex sequence generation tasks. Besides, adapter tuning is primarily applied with a focus on encoder-only self-supervised models. Our experiments show that prompting on Wav2Seq, a self-supervised encoder-decoder model, surpasses previous works in sequence generation tasks. It achieves a remarkable 53% relative improvement in word error rate for ASR and a 27% in F1 score for slot filling. Additionally, prompting competes with the FT method in the low-resource scenario. Moreover, we show the transferability of prompting and adapter tuning on Wav2Seq in cross-lingual ASR. When limited trainable parameters are involved, prompting and adapter tuning consistently outperform conventional FT across 7 languages. Notably, in the low-resource scenario, prompting consistently outperforms adapter tuning.
Although Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit impressive skills in various domains, their ability for mathematical reasoning within visual contexts has not been formally examined. Equipping LLMs and LMMs with this capability is vital for general-purpose AI assistants and showcases promising potential in education, data analysis, and scientific discovery. To bridge this gap, we present MathVista, a benchmark designed to amalgamate challenges from diverse mathematical and visual tasks. We first taxonomize the key task types, reasoning skills, and visual contexts from the literature to guide our selection from 28 existing math-focused and visual question answering datasets. Then, we construct three new datasets, IQTest, FunctionQA, and PaperQA, to accommodate for missing types of visual contexts. The problems featured often require deep visual understanding beyond OCR or image captioning, and compositional reasoning with rich domain-specific tools, thus posing a notable challenge to existing models. We conduct a comprehensive evaluation of 11 prominent open-source and proprietary foundation models (LLMs, LLMs augmented with tools, and LMMs), and early experiments with GPT-4V. The best-performing model, Multimodal Bard, achieves only 58% of human performance (34.8% vs 60.3%), indicating ample room for further improvement. Given this significant gap, MathVista fuels future research in the development of general-purpose AI agents capable of tackling mathematically intensive and visually rich real-world tasks. Preliminary tests show that MathVista also presents challenges to GPT-4V, underscoring the benchmark's importance. The project is available at https://mathvista.github.io/.
This paper introduces a novel voice conversion (VC) model, guided by text instructions such as "articulate slowly with a deep tone" or "speak in a cheerful boyish voice". Unlike traditional methods that rely on reference utterances to determine the attributes of the converted speech, our model adds versatility and specificity to voice conversion. The proposed VC model is a neural codec language model which processes a sequence of discrete codes, resulting in the code sequence of converted speech. It utilizes text instructions as style prompts to modify the prosody and emotional information of the given speech. In contrast to previous approaches, which often rely on employing separate encoders like prosody and content encoders to handle different aspects of the source speech, our model handles various information of speech in an end-to-end manner. Experiments have demonstrated the impressive capabilities of our model in comprehending instructions and delivering reasonable results.
Zero-shot cross-lingual transfer is a central task in multilingual NLP, allowing models trained in languages with more sufficient training resources to generalize to other low-resource languages. Earlier efforts on this task use parallel corpora, bilingual dictionaries, or other annotated alignment data to improve cross-lingual transferability, which are typically expensive to obtain. In this paper, we propose a simple yet effective method, SALT, to improve the zero-shot cross-lingual transfer of the multilingual pretrained language models without the help of such external data. By incorporating code-switching and embedding mixup with self-augmentation, SALT effectively distills cross-lingual knowledge from the multilingual PLM and enhances its transferability on downstream tasks. Experimental results on XNLI and PAWS-X show that our method is able to improve zero-shot cross-lingual transferability without external data. Our code is available at https://github.com/luka-group/SALT.
Text language models have shown remarkable zero-shot capability in generalizing to unseen tasks when provided with well-formulated instructions. However, existing studies in speech processing primarily focus on limited or specific tasks. Moreover, the lack of standardized benchmarks hinders a fair comparison across different approaches. Thus, we present Dynamic-SUPERB, a benchmark designed for building universal speech models capable of leveraging instruction tuning to perform multiple tasks in a zero-shot fashion. To achieve comprehensive coverage of diverse speech tasks and harness instruction tuning, we invite the community to collaborate and contribute, facilitating the dynamic growth of the benchmark. To initiate, Dynamic-SUPERB features 55 evaluation instances by combining 33 tasks and 22 datasets. This spans a broad spectrum of dimensions, providing a comprehensive platform for evaluation. Additionally, we propose several approaches to establish benchmark baselines. These include the utilization of speech models, text language models, and the multimodal encoder. Evaluation results indicate that while these baselines perform reasonably on seen tasks, they struggle with unseen ones. We also conducted an ablation study to assess the robustness and seek improvements in the performance. We release all materials to the public and welcome researchers to collaborate on the project, advancing technologies in the field together.