Related papers: Op-Fed: Opinion, Stance, and Monetary Policy Annot…
Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct. Very little work adequately exploits unannotated data -- such as discourse markers between sentences -- mainly because of…
Off-policy evaluation (OPE) in contextual bandits has seen rapid adoption in real-world systems, since it enables offline evaluation of new policies using only historic log data. Unfortunately, when the number of actions is large, existing…
Since previous studies on open-domain targeted sentiment analysis are limited in dataset domain variety and sentence level, we propose a novel dataset consisting of 6,013 human-labeled data to extend the data domains in topics of interest…
Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate…
Closed-loop decision-making systems (e.g., lending, screening, or recidivism risk assessment) often operate under fairness and service constraints while inducing feedback effects: decisions change who appears in the future, yielding…
Active learning algorithms automatically identify the most informative samples from large amounts of unlabeled data and tremendously reduce human annotation effort in inducing a machine learning model. In a conventional active learning…
Reinforcement Learning from Human Feedback (RLHF) has become the standard for aligning Large Language Models (LLMs), yet its efficacy is bottlenecked by the high cost of acquiring preference data, especially in low-resource and expert…
Large language models increasingly shape the information people consume: they are embedded in search, consulted for professional advice, deployed as agents, and used as a first stop for questions about policy, ethics, health, and politics.…
Neural machine translation (NMT) is sensitive to domain shift. In this paper, we address this problem in an active learning setting where we can spend a given budget on translating in-domain data, and gradually fine-tune a pre-trained…
While the classic off-policy evaluation (OPE) literature commonly assumes decision time points to be evenly spaced for simplicity, in many real-world scenarios, such as those involving user-initiated visits, decisions are made at…
The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF),…
Large language models (LLMs) have demonstrated significant advancements in error handling. Current error-handling works are performed in a passive manner, with explicit error-handling instructions. However, in real-world scenarios, explicit…
Moral framing and sentiment can affect a variety of online and offline behaviors, including donation, environmental action, political engagement, and protest. Various computational methods in Natural Language Processing (NLP) have been used…
Opinion phrase extraction is one of the key tasks in fine-grained sentiment analysis. While opinion expressions could be generic subjective expressions, aspect specific opinion expressions contain both the aspect as well as the opinion…
We can often detect from a person's utterances whether he/she is in favor of or against a given target entity -- their stance towards the target. However, a person may express the same stance towards a target by using negative or positive…
Sentiment analysis is a vital tool for uncovering insights from financial articles, news, and social media, shaping our understanding of market movements. Despite the impressive capabilities of large language models (LLMs) in financial…
Large language models are increasingly used to annotate texts, but their outputs reflect some human perspectives better than others. Existing methods for correcting LLM annotation error assume a single ground truth. However, this assumption…
We explore off-policy evaluation and learning (OPE/L) in contextual combinatorial bandits (CCB), where a policy selects a subset in the action space. For example, it might choose a set of furniture pieces (a bed and a drawer) from available…
This paper proposes a novel approach for constructing effective personalized policies when the observed data lacks counter-factual information, is biased and possesses many features. The approach is applicable in a wide variety of settings…
Recently, influence functions present an apparatus for achieving explainability for deep neural models by quantifying the perturbation of individual train instances that might impact a test prediction. Our objectives in this paper are…