Evaluation of dialogue systems requires assessing various aspects, among which appropriateness holds significance as a core element of communicative language competence. However, current evaluations heavily rely on human judgments, which are time-consuming, labor-intensive, prone to biases, and lacking objectivity. In this paper, we introduce Dialogue Act Appropriateness (DAA), a novel method that utilizes the underlying patterns of dialogue act transitions to evaluate the appropriateness of chatbot responses. We learn transition patterns from human-human dialogue corpora, evaluating chatbot appropriateness by measuring the similarity of their transition patterns to those observed in human-human dialogues. To validate DAA, we annotate a test dataset by manually evaluating the appropriateness of dialogues from multiple chatbot systems. The experimental results demonstrate a strong correlation between our evaluation metric and human ratings, establishing the reliability of DAA as a measure of dialogue appropriateness.

Automatic Evaluate Dialogue Appropriateness by Using Dialogue Act

Despite tremendous advances in AI, it remains a significant challenge to develop interactive task guidance systems that can offer situated, personalized guidance and assist humans in various tasks. 
These systems need to have a sophisticated understanding of the user as well as the environment, and make timely accurate decisions on when and what to say. To address this issue, we created a new multimodal benchmark dataset, Watch, Talk and Guide (WTaG) based on natural interaction between a human user and a human instructor. We further proposed two tasks: User and Environment Understanding, and Instructor Decision Making. We leveraged several foundation models to study to what extent these models can be quickly adapted to perceptually enabled task guidance. Our quantitative, qualitative, and human evaluation results show that these models can demonstrate fair performances in some cases with no task-specific training, but a fast and reliable adaptation remains a significant challenge. Our benchmark and baselines will provide a stepping stone for future work on situated task guidance.

Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?

Offensive speech detection is a key component of content moderation. However, what is offensive can be highly subjective. This paper investigates how machine and human moderators disagree on what is offensive when it comes to real-world social web political discourse. We show that (1) there is extensive disagreement among the moderators (humans and machines); and (2) human and large-language-model classifiers are unable to predict how other human raters will respond, based on their political leanings. For (1), we conduct a ***noise audit*** at an unprecedented scale that combines both machine and human responses. For (2), we introduce a first-of-its-kind dataset of ***vicarious offense***. Our noise audit reveals that moderation outcomes vary wildly across different machine moderators. Our experiments with human moderators suggest that political leanings combined with sensitive issues affect both first-person and vicarious offense. The dataset is available through https://github.com/Homan-Lab/voiced.

Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive | VIDEO

A crucial challenge for generative large language models (LLMs) is diversity: when a user's prompt is under-specified, models may follow implicit assumptions while generating a response, which may result in homogenization of the responses, as well as certain demographic groups being under-represented or even erased from the generated responses. In this paper, we formalize the problem diversity of representation in LLM generations. We present evaluation datasets and propose metrics to measure diversity in generated responses along people and culture axes. We find that LLMs understand the notion of diversity, and that they can reason and critique their own responses for that goal. This finding motivated a new prompting technique called collective-critique and self-voting (CCSV) to self-improve people diversity of LLMs by tapping into its diversity reasoning capabilities, without relying on handcrafted examples or prompt tuning. Extensive empirical experiments with both human and automated evaluations show that our proposed approach is effective at improving people and culture diversity, and outperforms all baseline methods by a large margin.

Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting

Feature attribution scores are used for explaining the prediction of a text classifier to users by highlighting a k number of tokens. In this work, we propose a way to determine the number of optimal k tokens that should be displayed from sequential properties of the attribution scores. Our approach is dynamic across sentences, method-agnostic, and deals with sentence length bias. We compare agreement between multiple methods and humans on an NLI task, using fixed k and dynamic k. We find that perturbation-based methods and Vanilla Gradient exhibit highest agreement on most method--method and method--human agreement metrics with a static k. Their advantage over other methods disappears with dynamic ks which mainly improve Integrated Gradient and GradientXInput. To our knowledge, this is the first evidence that sequential properties of attribution scores are informative for consolidating attribution signals for human interpretation.

Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods

Human feedback is increasingly used to steer the behaviours of Large Language Models (LLMs). However, it is unclear how to collect and incorporate feedback in a way that is efficient, effective and unbiased, especially for highly subjective human preferences and values. In this paper, we survey existing approaches for learning from human feedback, drawing on 95 papers primarily from the ACL and arXiv repositories. First, we summarise the past, pre-LLM trends for integrating human feedback into language models. Second, we give an overview of present techniques and practices, as well as the motivations for using feedback; conceptual frameworks for defining values and preferences; and how feedback is collected and from whom. Finally, we encourage a better future of feedback learning in LLMs by raising five unresolved conceptual and practical challenges.

The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values | VIDEO

The ability to automatically generate accurate protocols for scientific experiments would represent a major step towards the automation of science. Large Language Models (LLMs) have impressive capabilities on a wide range of tasks, such as question answering and the generation of coherent text and code. However, LLMs can struggle with multi-step problems and long-term planning, which are crucial for designing scientific experiments. Moreover, evaluation of the accuracy of scientific protocols is challenging, because experiments can be described correctly in many different ways, require expert knowledge to evaluate, and cannot usually be executed automatically. Here we present an automatic evaluation framework for the task of planning experimental protocols, and we introduce BioProt: a dataset of biology protocols with corresponding pseudocode representations. To measure performance on generating scientific protocols, we use an LLM to convert a natural language protocol into pseudocode, and then evaluate an LLM's ability to reconstruct the pseudocode from a high-level description and a list of admissible pseudocode functions. We evaluate GPT-3 and GPT-4 on this task and explore their robustness. We externally validate the utility of pseudocode representations of text by generating accurate novel protocols using retrieved pseudocode, and we run a generated protocol successfully in our biological laboratory. Our framework is extensible to the evaluation and improvement of language model

BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology | VIDEO

Recent work has shown the promise of learning with human feedback paradigms to produce human-determined high-quality text. Existing works use human feedback to train large language models (LLMs) in general domain abstractive summarization and have obtained summary quality exceeding traditional likelihood training. In this paper, we focus on a less explored form of human feedback -- Human Edits. We propose Sequence Alignment (un)Likelihood Training (SALT), a novel technique to use both the human-edited and model-generated data together in the training loop. In addition, we demonstrate simulating Human Edits with ground truth summaries coming from existing training data -- Imitation edits, along with the model-generated summaries obtained after the training, to reduce the need for expensive human-edit data. In our experiments, we extend human feedback exploration from general domain summarization to medical domain summarization. Our results demonstrate the effectiveness of SALT in improving the summary quality with Human and Imitation Edits. Through additional experiments, we show that SALT outperforms the conventional RLHF method (designed for human preferences) -- DPO, when applied to human-edit data. We hope the evidence in our paper prompts researchers to explore, collect, and better use different human feedback approaches scalably.

Improving Summarization with Human Edits | VIDEO

Human experts write summaries using different techniques, including extracting a sentence from the document and rewriting it, or fusing various information from the document to abstract it. These techniques are flexible and thus difficult to be imitated by any single method. To address this issue, we propose an adaptive model, GEMINI, that integrates a rewriter and a generator to mimic the sentence rewriting and abstracting techniques, respectively. GEMINI adaptively chooses to rewrite a specific document sentence or generate a summary sentence from scratch. Experiments demonstrate that our adaptive approach outperforms the pure abstractive and rewriting baselines on three benchmark datasets, achieving the best results on WikiHow. Interestingly, empirical results show that the human summary styles of summary sentences are consistently predictable given their context. We release our code and model at \url{https://github.com/baoguangsheng/gemini}.

GEMINI: Controlling The Sentence-Level Summary Style in Abstractive Text Summarization | VIDEO

Existing lexical substitution (LS) benchmarks were collected by asking human annotators to think of substitutes from memory, resulting in benchmarks with limited coverage and relatively small scales. To overcome this problem, we propose a novel annotation method to construct an LS dataset based on human and machine collaboration. Based on our annotation method, we construct the first Chinese LS dataset CHNLS which consists of 33,695 instances and 144,708 substitutes, covering three text genres (News, Novel, and Wikipedia). Specifically, we first combine four unsupervised LS methods as an ensemble method to generate the candidate substitutes, and then let human annotators judge these candidates or add new ones. This collaborative process combines the diversity of machine-generated substitutes with the expertise of human annotators. Experimental results that the ensemble method outperforms other LS methods. To our best knowledge, this is the first study for the Chinese LS task.

Chinese Lexical Substitution: Dataset and Method

Text classification tasks often encounter few-shot scenarios with limited labeled data, and addressing data scarcity is crucial. Data augmentation with mixup merges sample pairs to generate new pseudos, which can relieve the data deficiency issue in text classification. However, the quality of pseudo-samples generated by mixup exhibits significant variations. Most of the mixup methods fail to consider the varying degree of learning difficulty in different stages of training. And mixup generates new samples with one-hot labels, which encourages the model to produce a high prediction score for the correct class that is much larger than other classes, resulting in the model's over-confidence. In this paper, we propose a self-evolution learning (SE) based mixup approach for data augmentation in text classification, which can generate more adaptive and model-friendly pseudo samples for the model training. SE caters to the growth of the model learning ability and adapts to the ability when generating training samples. To alleviate the model over-confidence, we introduce an instance-specific label smoothing regularization approach, which linearly interpolates the model’s output and one-hot labels of the original samples to generate new soft labels for label mixing up. Through experimental analysis, experiments show that our SE brings consistent and significant improvements upon different mixup methods. In-depth analyses demonstrate that SE enhances the model's generalization ability.

Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks

Rich and diverse knowledge bases (KB) are foundational building blocks for online knowledge sharing communities such as StackOverflow and Quora, and applications such as conversational assistants (aka chatbots). A popular format for knowledge bases is question-answer pairs (or FAQs), where questions are designed to accurately match a multitude of queries. In this paper, we address the problem of automatic creation of such Q\&A-based knowledge bases from domain-specific, long-form textual content (e.g., web articles). Specifically, we consider the problem of question generation, which is the task of generating questions given a paragraph of text as input, with a goal to achieve both diversity and fidelity of the generated questions. Towards this goal we propose PROTEGE, a diverse question generation framework which consists of (1) a novel encoder-decoder based Large Language Model (LLM) architecture which can take a variety of prompts and generate a diverse set of candidate questions, and (2) a hill-climbing algorithm that maximizes a sub-modular objective function to balance diversity with fidelity. Through our experiments on three popular public Q\&A datasets, we demonstrate that PROTEGE improves diversity by +16% and fidelity by +8% over diverse beam search and prompt-based baselines.

Underline digital video library

Automatic Evaluate Dialogue Appropriateness by Using Dialogue Act

Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?

Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive | VIDEO

Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting

Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods

The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values | VIDEO

BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology | VIDEO

Improving Summarization with Human Edits | VIDEO

GEMINI: Controlling The Sentence-Level Summary Style in Abstractive Text Summarization | VIDEO

Chinese Lexical Substitution: Dataset and Method

Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks

PROTEGE: Prompt-based Diverse Question Generation from Web Articles

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES