Traditionally, natural language processing (NLP) models often use a rich set of features created by linguistic expertise, such as semantic representations. However, in the era of large language models (LLMs), more and more tasks are turned into generic, end-to-end sequence generation problems. In this paper, we investigate the question: what is the role of semantic representations in the era of LLMs? Specifically, we investigate the effect of Abstract Meaning Representation (AMR) across five diverse NLP tasks. We propose an AMR-driven chain-of-thought prompting method, which we call AMRCoT, and find that it generally hurts performance more than it helps. To investigate what AMR may have to offer on these tasks, we conduct a series of analysis experiments. We find that it is difficult to predict which input examples AMR may help or hurt on, but errors tend to arise with multi-word expressions, named entities, and in the final inference step where the LLM must connect its reasoning over the AMR to its prediction. We recommend focusing on these areas for future work in semantic representations for LLMs. Our code: https://github.com/causalNLP/amr_llm.
A patient's digital twin is a computational model that describes the evolution of their health over time. Digital twins have the potential to revolutionize medicine by enabling individual-level computer simulations of human health, which can be used to conduct more efficient clinical trials or to recommend personalized treatment options. Due to the overwhelming complexity of human biology, machine learning approaches that leverage large datasets of historical patients' longitudinal health records to generate patients' digital twins are more tractable than potential mechanistic models. In this manuscript, we describe a neural network architecture that can learn conditional generative models of clinical trajectories, which we call Digital Twin Generators (DTGs), that can create digital twins of individual patients. We show that the same neural network architecture can be trained to generate accurate digital twins for patients across 13 different indications simply by changing the training set and tuning hyperparameters. By introducing a general purpose architecture, we aim to unlock the ability to scale machine learning approaches to larger datasets and across more indications so that a digital twin could be created for any patient in the world.
Algorithms frequently assist, rather than replace, human decision-makers. However, the design and analysis of algorithms often focus on predicting outcomes and do not explicitly model their effect on human decisions. This discrepancy between the design and role of algorithmic assistants becomes of particular concern in light of empirical evidence that suggests that algorithmic assistants again and again fail to improve human decisions. In this article, we formalize the design of recommendation algorithms that assist human decision-makers without making restrictive ex-ante assumptions about how recommendations affect decisions. We formulate an algorithmic-design problem that leverages the potential-outcomes framework from causal inference to model the effect of recommendations on a human decision-maker's binary treatment choice. Within this model, we introduce a monotonicity assumption that leads to an intuitive classification of human responses to the algorithm. Under this monotonicity assumption, we can express the human's response to algorithmic recommendations in terms of their compliance with the algorithm and the decision they would take if the algorithm sends no recommendation. We showcase the utility of our framework using an online experiment that simulates a hiring task. We argue that our approach explains the relative performance of different recommendation algorithms in the experiment, and can help design solutions that realize human-AI complementarity.
We consider Dynamic Treatment Regimes (DTRs) with one sided non-compliance that arise in applications such as digital recommendations and adaptive medical trials. These are settings where decision makers encourage individuals to take treatments over time, but adapt encouragements based on previous encouragements, treatments, states, and outcomes. Importantly, individuals may choose to (not) comply with a treatment recommendation, whenever it is made available to them, based on unobserved confounding factors. We provide non-parametric identification, estimation, and inference for Dynamic Local Average Treatment Effects, which are expected values of multi-period treatment contrasts among appropriately defined complier subpopulations. Under standard assumptions in the Instrumental Variable and DTR literature, we show that one can identify local average effects of contrasts that correspond to offering treatment at any single time step. Under an additional cross-period effect-compliance independence assumption, which is satisfied in Staggered Adoption settings and a generalization of them, which we define as Staggered Compliance settings, we identify local average treatment effects of treating in multiple time periods.
While the topic of listening context is widely studied in the literature of music recommender systems, the integration of regular user behavior is often omitted. In this paper, we propose PACE (PAttern-based user Consumption Embedding), a framework for building user embeddings that takes advantage of periodic listening behaviors. PACE leverages users' multichannel time-series consumption patterns to build understandable user vectors. We believe the embeddings learned with PACE unveil much about the repetitive nature of user listening dynamics. By applying this framework on long-term user histories, we evaluate the embeddings through a predictive task of activities performed while listening to music. The validation task's interest is two-fold, while it shows the relevance of our approach, it also offers an insightful way of understanding users' musical consumption habits.
Prompt engineering is crucial for harnessing the potential of large language models (LLMs), especially in the medical domain where specialized terminology and phrasing is used. However, the efficacy of prompt engineering in the medical domain remains to be explored. In this work, 114 recent studies (2022-2024) applying prompt engineering in medicine, covering prompt learning (PL), prompt tuning (PT), and prompt design (PD) are reviewed. PD is the most prevalent (78 articles). In 12 papers, PD, PL, and PT terms were used interchangeably. ChatGPT is the most commonly used LLM, with seven papers using it for processing sensitive clinical data. Chain-of-Thought emerges as the most common prompt engineering technique. While PL and PT articles typically provide a baseline for evaluating prompt-based approaches, 64% of PD studies lack non-prompt-related baselines. We provide tables and figures summarizing existing work, and reporting recommendations to guide future research contributions.
Next basket recommendation (NBR) is a special type of sequential recommendation that is increasingly receiving attention. So far, most NBR studies have focused on optimizing the accuracy of the recommendation, whereas optimizing for beyond-accuracy metrics, e.g., item fairness and diversity remains largely unexplored. Recent studies into NBR have found a substantial performance difference between recommending repeat items and explore items. Repeat items contribute most of the users' perceived accuracy compared with explore items. Informed by these findings, we identify a potential "short-cut" to optimize for beyond-accuracy metrics while maintaining high accuracy. To leverage and verify the existence of such short-cuts, we propose a plug-and-play two-step repetition-exploration (TREx) framework that treats repeat items and explores items separately, where we design a simple yet highly effective repetition module to ensure high accuracy, while two exploration modules target optimizing only beyond-accuracy metrics. Experiments are performed on two widely-used datasets w.r.t. a range of beyond-accuracy metrics, viz. five fairness metrics and three diversity metrics. Our experimental results verify the effectiveness of TREx. Prima facie, this appears to be good news: we can achieve high accuracy and improved beyond-accuracy metrics at the same time. However, we argue that the real-world value of our algorithmic solution, TREx, is likely to be limited and reflect on the reasonableness of the evaluation setup. We end up challenging existing evaluation paradigms, particularly in the context of beyond-accuracy metrics, and provide insights for researchers to navigate potential pitfalls and determine reasonable metrics to consider when optimizing for accuracy and beyond-accuracy metrics.
As recommender systems are indispensable in various domains such as job searching and e-commerce, providing equitable recommendations to users with different sensitive attributes becomes an imperative requirement. Prior approaches for enhancing fairness in recommender systems presume the availability of all sensitive attributes, which can be difficult to obtain due to privacy concerns or inadequate means of capturing these attributes. In practice, the efficacy of these approaches is limited, pushing us to investigate ways of promoting fairness with limited sensitive attribute information. Toward this goal, it is important to reconstruct missing sensitive attributes. Nevertheless, reconstruction errors are inevitable due to the complexity of real-world sensitive attribute reconstruction problems and legal regulations. Thus, we pursue fair learning methods that are robust to reconstruction errors. To this end, we propose Distributionally Robust Fair Optimization (DRFO), which minimizes the worst-case unfairness over all potential probability distributions of missing sensitive attributes instead of the reconstructed one to account for the impact of the reconstruction errors. We provide theoretical and empirical evidence to demonstrate that our method can effectively ensure fairness in recommender systems when only limited sensitive attributes are accessible.
Session-based recommendation (SBR) aims to predict the following item a user will interact with during an ongoing session. Most existing SBR models focus on designing sophisticated neural-based encoders to learn a session representation, capturing the relationship among session items. However, they tend to focus on the last item, neglecting diverse user intents that may exist within a session. This limitation leads to significant performance drops, especially for longer sessions. To address this issue, we propose a novel SBR model, called Multi-intent-aware Session-based Recommendation Model (MiaSRec). It adopts frequency embedding vectors indicating the item frequency in session to enhance the information about repeated items. MiaSRec represents various user intents by deriving multiple session representations centered on each item and dynamically selecting the important ones. Extensive experimental results show that MiaSRec outperforms existing state-of-the-art SBR models on six datasets, particularly those with longer average session length, achieving up to 6.27% and 24.56% gains for MRR@20 and Recall@20. Our code is available at https://github.com/jin530/MiaSRec.
Designing preference elicitation (PE) methodologies that can quickly ascertain a user's top item preferences in a cold-start setting is a key challenge for building effective and personalized conversational recommendation (ConvRec) systems. While large language models (LLMs) constitute a novel technology that enables fully natural language (NL) PE dialogues, we hypothesize that monolithic LLM NL-PE approaches lack the multi-turn, decision-theoretic reasoning required to effectively balance the NL exploration and exploitation of user preferences towards an arbitrary item set. In contrast, traditional Bayesian optimization PE methods define theoretically optimal PE strategies, but fail to use NL item descriptions or generate NL queries, unrealistically assuming users can express preferences with direct item ratings and comparisons. To overcome the limitations of both approaches, we formulate NL-PE in a Bayesian Optimization (BO) framework that seeks to generate NL queries which actively elicit natural language feedback to reduce uncertainty over item utilities to identify the best recommendation. We demonstrate our framework in a novel NL-PE algorithm, PEBOL, which uses Natural Language Inference (NLI) between user preference utterances and NL item descriptions to maintain preference beliefs and BO strategies such as Thompson Sampling (TS) and Upper Confidence Bound (UCB) to guide LLM query generation. We numerically evaluate our methods in controlled experiments, finding that PEBOL achieves up to 131% improvement in MAP@10 after 10 turns of cold start NL-PE dialogue compared to monolithic GPT-3.5, despite relying on a much smaller 400M parameter NLI model for preference inference.