arXiv subjects

Lucas Dixon

Publications and source records attributed to Lucas Dixon.

At least 37 records · Page 2Linked to original sources

arXiv2024

"We Need Structured Output": Towards User-centered Constraints on Large Language Model Output

Large language models can produce creative and diverse responses. However, to integrate them into current developer workflows, it is essential to constrain their outputs to follow specific formats or standards. In this work, we surveyed 51 experienced industry professionals to understand the range of scenarios and motivations driving the need for output constraints from a user-centered perspective. We identified 134 concrete use cases for constraints at two levels: low-level, which ensures the output adhere to a structured format and an appropriate length, and high-level, which requires the output to follow semantic and stylistic guidelines without hallucination. Critically, applying output constraints could not only streamline the currently repetitive process of developing, testing, and integrating LLM prompts for developers, but also enhance the user experience of LLM-powered features and applications. We conclude with a discussion on user preferences and needs towards articulating intended constraints for LLMs, alongside an initial design for a constraint prototyping tool.

cs.HC↗

arXiv2024

Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics

We explore a strategy to handle controversial topics in LLM-based chatbots based on Wikipedia's Neutral Point of View (NPOV) principle: acknowledge the absence of a single true answer and surface multiple perspectives. We frame this as retrieval augmented generation, where perspectives are retrieved from a knowledge base and the LLM is tasked with generating a fluent and faithful response from the given perspectives. As a starting point, we use a deterministic retrieval system and then focus on common LLM failure modes that arise during this approach to text generation, namely hallucination and coverage errors. We propose and evaluate three methods to detect such errors based on (1) word-overlap, (2) salience, and (3) LLM-based classifiers. Our results demonstrate that LLM-based classifiers, even when trained only on synthetic errors, achieve high error detection performance, with ROC AUC scores of 95.3% for hallucination and 90.5% for coverage error detection on unambiguous error cases. We show that when no training data is available, our other methods still yield good results on hallucination (84.0%) and coverage error (85.2%) detection.

cs.CL↗

arXiv2024

LLM Comparator: Visual Analytics for Side-by-Side Evaluation of Large Language Models

Automatic side-by-side evaluation has emerged as a promising approach to evaluating the quality of responses from large language models (LLMs). However, analyzing the results from this evaluation approach raises scalability and interpretability challenges. In this paper, we present LLM Comparator, a novel visual analytics tool for interactively analyzing results from automatic side-by-side evaluation. The tool supports interactive workflows for users to understand when and why a model performs better or worse than a baseline model, and how the responses from two models are qualitatively different. We iteratively designed and developed the tool by closely working with researchers and engineers at a large technology company. This paper details the user challenges we identified, the design and development of the tool, and an observational study with participants who regularly evaluate their models.

cs.HC↗

arXiv2023

Towards Agile Text Classifiers for Everyone

Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digital assistants and chatbots. However, different policies require different classifiers, and safety policies themselves improve from iteration and adaptation. This paper introduces and evaluates methods for agile text classification, whereby classifiers are trained using small, targeted datasets that can be quickly developed for a particular policy. Experimenting with 7 datasets from three safety-related domains, comprising 15 annotation schemes, led to our key finding: prompt-tuning large language models, like PaLM 62B, with a labeled dataset of as few as 80 examples can achieve state-of-the-art performance. We argue that this enables a paradigm shift for text classification, especially for models supporting safer online discourse. Instead of collecting millions of examples to attempt to create universal safety classifiers over months or years, classifiers could be tuned using small datasets, created by individuals or small organizations, tailored for specific use cases, and iterated on and adapted in the time-span of a day.

cs.CL↗

arXiv2023

Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences

Traditional recommender systems leverage users' item preference history to recommend novel content that users may like. However, modern dialog interfaces that allow users to express language-based preferences offer a fundamentally different modality for preference input. Inspired by recent successes of prompting paradigms for large language models (LLMs), we study their use for making recommendations from both item-based and language-based preferences in comparison to state-of-the-art item-based collaborative filtering (CF) methods. To support this investigation, we collect a new dataset consisting of both item-based and language-based preferences elicited from users along with their ratings on a variety of (biased) recommended items and (unbiased) random items. Among numerous experimental results, we find that LLMs provide competitive recommendation performance for pure language-based preferences (no item preferences) in the near cold-start case in comparison to item-based CF methods, despite having no supervised training for this specific task (zero-shot) or only a few labels (few-shot). This is particularly promising as language-based preference representations are more explainable and scrutable than item-based or vector-based representations.

cs.IR↗

arXiv2023

Large Language Models for User Interest Journeys

Large language models (LLMs) have shown impressive capabilities in natural language understanding and generation. Their potential for deeper user understanding and improved personalized user experience on recommendation platforms is, however, largely untapped. This paper aims to address this gap. Recommender systems today capture users' interests through encoding their historical activities on the platforms. The generated user representations are hard to examine or interpret. On the other hand, if we were to ask people about interests they pursue in their life, they might talk about their hobbies, like I just started learning the ukulele, or their relaxation routines, e.g., I like to watch Saturday Night Live, or I want to plant a vertical garden. We argue, and demonstrate through extensive experiments, that LLMs as foundation models can reason through user activities, and describe their interests in nuanced and interesting ways, similar to how a human would. We define interest journeys as the persistent and overarching user interests, in other words, the non-transient ones. These are the interests that we believe will benefit most from the nuanced and personalized descriptions. We introduce a framework in which we first perform personalized extraction of interest journeys, and then summarize the extracted journeys via LLMs, using techniques like few-shot prompting, prompt-tuning and fine-tuning. Together, our results in prompting LLMs to name extracted user journeys in a large-scale industrial platform demonstrate great potential of these models in providing deeper, more interpretable, and controllable user understanding. We believe LLM powered user understanding can be a stepping stone to entirely new user experiences on recommendation platforms that are journey-aware, assistive, and enabling frictionless conversation down the line.

cs.CL↗

arXiv2023

KNNs of Semantic Encodings for Rating Prediction

This paper explores a novel application of textual semantic similarity to user-preference representation for rating prediction. The approach represents a user's preferences as a graph of textual snippets from review text, where the edges are defined by semantic similarity. This textual, memory-based approach to rating prediction enables review-based explanations for recommendations. The method is evaluated quantitatively, highlighting that leveraging text in this way outperforms both strong memory-based and model-based collaborative filtering baselines.

cs.CL↗

arXiv2023

Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs

Training data attribution (TDA) methods offer to trace a model's prediction on any given example back to specific influential training examples. Existing approaches do so by assigning a scalar influence score to each training example, under a simplifying assumption that influence is additive. But in reality, we observe that training examples interact in highly non-additive ways due to factors such as inter-example redundancy, training order, and curriculum learning effects. To study such interactions, we propose Simfluence, a new paradigm for TDA where the goal is not to produce a single influence score per example, but instead a training run simulator: the user asks, ``If my model had trained on example $z_1$, then $z_2$, ..., then $z_n$, how would it behave on $z_{test}$?''; the simulator should then output a simulated training run, which is a time series predicting the loss on $z_{test}$ at every step of the simulated run. This enables users to answer counterfactual questions about what their model would have learned under different training curricula, and to directly see where in training that learning would occur. We present a simulator, Simfluence-Linear, that captures non-additive interactions and is often able to predict the spiky trajectory of individual example losses with surprising fidelity. Furthermore, we show that existing TDA methods such as TracIn and influence functions can be viewed as special cases of Simfluence-Linear. This enables us to directly compare methods in terms of their simulation accuracy, subsuming several prior TDA approaches to evaluation. In experiments on large language model (LLM) fine-tuning, we show that our method predicts loss trajectories with much higher accuracy than existing TDA methods (doubling Spearman's correlation and reducing mean-squared error by 75%) across several tasks, models, and training methods.

cs.LG↗

arXiv2023

Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis

Each year, expert-level performance is attained in increasingly-complex multiagent domains, where notable examples include Go, Poker, and StarCraft II. This rapid progression is accompanied by a commensurate need to better understand how such agents attain this performance, to enable their safe deployment, identify limitations, and reveal potential means of improving them. In this paper we take a step back from performance-focused multiagent learning, and instead turn our attention towards agent behavior analysis. We introduce a model-agnostic method for discovery of behavior clusters in multiagent domains, using variational inference to learn a hierarchy of behaviors at the joint and local agent levels. Our framework makes no assumption about agents' underlying learning algorithms, does not require access to their latent states or policies, and is trained using only offline observational data. We illustrate the effectiveness of our method for enabling the coupled understanding of behaviors at the joint and local agent level, detection of behavior changepoints throughout training, discovery of core behavioral concepts, demonstrate the approach's scalability to a high-dimensional multiagent MuJoCo control domain, and also illustrate that the approach can disentangle previously-trained policies in OpenAI's hide-and-seek domain.

cs.LG↗

arXiv2023

Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning

Pretrained large language models (LLMs) are able to solve a wide variety of tasks through transfer learning. Various explainability methods have been developed to investigate their decision making process. TracIn (Pruthi et al., 2020) is one such gradient-based method which explains model inferences based on the influence of training examples. In this paper, we explore the use of TracIn to improve model performance in the parameter-efficient tuning (PET) setting. We develop conversational safety classifiers via the prompt-tuning PET method and show how the unique characteristics of the PET regime enable TracIn to identify the cause for certain misclassifications by LLMs. We develop a new methodology for using gradient-based explainability techniques to improve model performance, G-BAIR: gradient-based automated iterative recovery. We show that G-BAIR can recover LLM performance on benchmarks after manually corrupting training labels. This suggests that influence methods like TracIn can be used to automatically perform data cleaning, and introduces the potential for interactive debugging and relabeling for PET-based transfer learning methods.

cs.CL↗

arXiv2022

Basic Elements of Logical Graphs

We considers how a particular kind of graph corresponds to multiplicative intuitionistic linear logic formula. The main feature of the graphical notation is that it absorbs certain symmetries between conjunction and implication. We look at the basic definitions and present details of an implementation in the functional programming language Standard ML. This provides a functional approach to graph traversal and demonstrates how graph isomorphism be implemented in just a few lines of readable code. This works takes the initial steps towards a graphical language and toolkit for working with logic formula and derivations.

cs.LO↗

arXiv2022

GLaM: Efficient Scaling of Language Models with Mixture-of-Experts

Scaling language models with more data, compute and parameters has driven significant progress in natural language processing. For example, thanks to scaling, GPT-3 was able to achieve strong results on in-context learning tasks. However, training these large dense models requires significant amounts of computing resources. In this paper, we propose and develop a family of language models named GLaM (Generalist Language Model), which uses a sparsely activated mixture-of-experts architecture to scale the model capacity while also incurring substantially less training cost compared to dense variants. The largest GLaM has 1.2 trillion parameters, which is approximately 7x larger than GPT-3. It consumes only 1/3 of the energy used to train GPT-3 and requires half of the computation flops for inference, while still achieving better overall zero-shot and one-shot performance across 29 NLP tasks.

cs.CL↗

arXiv2022

On Natural Language User Profiles for Transparent and Scrutable Recommendation

Natural interaction with recommendation and personalized search systems has received tremendous attention in recent years. We focus on the challenge of supporting people's understanding and control of these systems and explore a fundamentally new way of thinking about representation of knowledge in recommendation and personalization systems. Specifically, we argue that it may be both desirable and possible for algorithms that use natural language representations of users' preferences to be developed. We make the case that this could provide significantly greater transparency, as well as affordances for practical actionable interrogation of, and control over, recommendations. Moreover, we argue that such an approach, if successfully applied, may enable a major step towards systems that rely less on noisy implicit observations while increasing portability of knowledge of one's interests.

cs.IR↗

arXiv2021

Toxicity Detection can be Sensitive to the Conversational Context

User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on existing datasets will also tend to disregard context, making the detection of context-sensitive toxicity harder when it does occur. We construct and publicly release a dataset of 10,000 posts with two kinds of toxicity labels: (i) annotators considered each post with the previous one as context; and (ii) annotators had no additional context. Based on this, we introduce a new task, context sensitivity estimation, which aims to identify posts whose perceived toxicity changes if the context (previous post) is also considered. We then evaluate machine learning systems on this task, showing that classifiers of practical quality can be developed, and we show that data augmentation with knowledge distillation can improve the performance further. Such systems could be used to enhance toxicity detection datasets with more context-dependent posts, or to suggest when moderators should consider the parent posts, which often may be unnecessary and may otherwise introduce significant additional cost.

cs.CL↗

arXiv2021

Augmenting the User-Item Graph with Textual Similarity Models

This paper introduces a simple and effective form of data augmentation for recommender systems. A paraphrase similarity model is applied to widely available textual data, such as reviews and product descriptions, yielding new semantic relations that are added to the user-item graph. This increases the density of the graph without needing further labeled data. The data augmentation is evaluated on a variety of recommendation algorithms, using Euclidean, hyperbolic, and complex spaces, and over three categories of Amazon product reviews with differing characteristics. Results show that the data augmentation technique provides significant improvements to all types of models, with the most pronounced gains for knowledge graph-based recommenders, particularly in cold-start settings, leading to state-of-the-art performance.

cs.CL↗

arXiv2021

Civil Rephrases Of Toxic Texts With Self-Supervised Transformers

Platforms that support online commentary, from social networks to news sites, are increasingly leveraging machine learning to assist their moderation efforts. But this process does not typically provide feedback to the author that would help them contribute according to the community guidelines. This is prohibitively time-consuming for human moderators to do, and computational approaches are still nascent. This work focuses on models that can help suggest rephrasings of toxic comments in a more civil manner. Inspired by recent progress in unpaired sequence-to-sequence tasks, a self-supervised learning model is introduced, called CAE-T5. CAE-T5 employs a pre-trained text-to-text transformer, which is fine tuned with a denoising and cyclic auto-encoder loss. Experimenting with the largest toxicity detection dataset to date (Civil Comments) our model generates sentences that are more fluent and better at preserving the initial content compared to earlier text style transfer systems which we compare with using several scoring systems and human evaluation.

cs.CL↗

arXiv2020

Six Attributes of Unhealthy Conversation

We present a new dataset of approximately 44000 comments labeled by crowdworkers. Each comment is labelled as either 'healthy' or 'unhealthy', in addition to binary labels for the presence of six potentially 'unhealthy' sub-attributes: (1) hostile; (2) antagonistic, insulting, provocative or trolling; (3) dismissive; (4) condescending or patronising; (5) sarcastic; and/or (6) an unfair generalisation. Each label also has an associated confidence score. We argue that there is a need for datasets which enable research based on a broad notion of 'unhealthy online conversation'. We build this typology to encompass a substantial proportion of the individual comments which contribute to unhealthy online conversation. For some of these attributes, this is the first publicly available dataset of this scale. We explore the quality of the dataset, present some summary statistics and initial models to illustrate the utility of this data, and highlight limitations and directions for further research.

cs.CL↗

arXiv2020

Classifying Constructive Comments

We introduce the Constructive Comments Corpus (C3), comprised of 12,000 annotated news comments, intended to help build new tools for online communities to improve the quality of their discussions. We define constructive comments as high-quality comments that make a contribution to the conversation. We explain the crowd worker annotation scheme and define a taxonomy of sub-characteristics of constructiveness. The quality of the annotation scheme and the resulting dataset is evaluated using measurements of inter-annotator agreement, expert assessment of a sample, and by the constructiveness sub-characteristics, which we show provide a proxy for the general constructiveness concept. We provide models for constructiveness trained on C3 using both feature-based and a variety of deep learning approaches and demonstrate that these models capture general rather than topic- or domain-specific characteristics of constructiveness, through domain adaptation experiments. We examine the role that length plays in our models, as comment length could be easily gamed if models depend heavily upon this feature. By examining the errors made by each model and their distribution by length, we show that the best performing models are less correlated with comment length.The constructiveness corpus and our experiments pave the way for a moderation tool focused on promoting comments that make a contribution, rather than only filtering out undesirable content.

cs.CL↗