相关论文: GuardRails: Automated Suggestions for Clarifying A…

Generating accurate step-by-step reasoning is essential for Large Language Models (LLMs) to address complex problems and enhance robustness and interpretability. Despite the flux of research on developing advanced reasoning approaches,…

Large language models (LLMs) have exhibited impressive capabilities across a myriad of tasks, yet they occasionally yield undesirable outputs. We posit that these limitations are rooted in the foundational autoregressive architecture of…

This paper presents a framework that can interpret humans' navigation commands containing temporal elements and directly translate their natural language instructions into robot motion planning. Central to our framework is utilizing Large…

Task oriented Dialogue Systems generally employ intent detection systems in order to map user queries to a set of pre-defined intents. However, user queries appearing in natural language can be easily ambiguous and hence such a direct…

Fuzzy logic programming is a growing declarative paradigm aiming to integrate fuzzy logic into logic programming. One of the most difficult tasks when specifying a fuzzy logic program is determining the right weights for each rule, as well…

We introduce a novel framework named ClarifyGPT, which aims to enhance code generation by empowering LLMs with the ability to identify ambiguous requirements and ask targeted clarifying questions. In particular, ClarifyGPT first detects…

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains…

Prompt engineering is a challenging and important task due to the high sensitivity of Large Language Models (LLMs) to the given prompt and the inherent ambiguity of a textual task instruction. Automatic prompt engineering is essential to…

The evolution of autonomous driving has made remarkable advancements in recent years, evolving into a tangible reality. However, a human-centric large-scale adoption hinges on meeting a variety of multifaceted requirements. To ensure that…

Prompt underspecification is a common challenge when interacting with LLMs. In this paper, we present an in-depth analysis of this problem, showing that while LLMs can often infer unspecified requirements by default (41.1%), such behavior…

Functional specifications describe what program components do: the sufficient conditions to invoke a component's operations. They allow us to reason about the use of components in the closed world setting, where the component interacts with…

Explainable artificial intelligence techniques are developed at breakneck speed, but suitable evaluation approaches lag behind. With explainers becoming increasingly complex and a lack of consensus on how to assess their utility, it is…

The predominant challenge in weakly supervised semantic parsing is that of spurious programs that evaluate to correct answers for the wrong reasons. Prior work uses elaborate search strategies to mitigate the prevalence of spurious…

In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…

Safety policies define what constitutes safe and unsafe AI outputs, guiding data annotation and model development. However, annotation disagreement is pervasive and can stem from multiple sources such as operational failures (annotators…

Large language models (LLMs) have displayed an impressive ability to harness natural language to perform complex tasks. In this work, we explore whether we can leverage this learned ability to find and explain patterns in data.…

In large language model-based agents, memory serves as a critical capability for achieving personalization by storing and utilizing users' information. Although some previous studies have adopted memory to implement user personalization,…

Linear logic programming uses provability as the basis for computation. In the operational semantics based on provability, executing the additive-conjunctive goal $G_1 \& G_2$ from a program $P$ simply terminates with a success if both…

The art of heuristic design has traditionally been a human pursuit. While Large Language Models (LLMs) can generate code for search heuristics, their application has largely been confined to adjusting simple functions within human-crafted…

Explanations of an AI's function can assist human decision-makers, but the most useful explanation depends on the decision's context, referred to as the downstream task. User studies are necessary to determine the best explanations for each…