相关论文: Few-shot Policy (de)composition in Conversational …

Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual…

Large Language Models (LLMs) are increasingly integrated into real-world decision-making, including in the domain of public policy. Yet, their ability to comprehend and reason about policy-related content remains underexplored. To fill this…

Recent advances in Large Language Models (LLMs) have significantly reshaped the landscape of Natural Language Processing (NLP). Among the various prompting techniques, few-shot prompting has gained considerable attention for its…

The success of deep learning comes from its ability to capture the hierarchical structure of data by learning high-level representations defined in terms of low-level ones. In this paper we explore self-supervised learning of hierarchical…

Metaphor Components Identification (MCI) contributes to enhancing machine understanding of metaphors, thereby advancing downstream natural language processing tasks. However, the complexity, diversity, and dependency on context and…

Large Language models (LLMs) can be induced to solve non-trivial problems with "few-shot" prompts including illustrative problem-solution examples. Now if the few-shots also include "chain of thought" (CoT) explanations, which are of the…

In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals…

Inconsistent political statements represent a form of misinformation. They erode public trust and pose challenges to accountability, when left unnoticed. Detecting inconsistencies automatically could support journalists in asking…

Existing benchmarks for evaluating long-context language models (LCLMs) primarily focus on long-context recall, requiring models to produce short responses based on a few critical snippets while processing thousands of irrelevant tokens. We…

Programmable Logic Controllers (PLCs) are widely used in industrial automation to control physical systems. As PLC applications become increasingly complex, ensuring their correctness is crucial. Existing formal verification techniques…

We initiate the probabilistic analysis of linear programming (LP) decoding of low-density parity-check (LDPC) codes. Specifically, we show that for a random LDPC code ensemble, the linear programming decoder of Feldman et al. succeeds in…

Large Language Models (LLMs) often exhibit factual inconsistencies and logical decay in extended, multi-turn dialogues, a challenge stemming from their reliance on static, pre-trained knowledge and an inability to reason adaptively over the…

Fault tolerance in quantum protocols requires contributions from error-correcting codes and their suitable decoders. Quantum Low-Density Parity Check (QLDPC) codes are one of the most explored quantum codes that have good coding rate and…

Large Language Models (LLMs) prompted to generate chain-of-thought (CoT) exhibit impressive reasoning capabilities. Recent attempts at prompt decomposition toward solving complex, multi-step reasoning problems depend on the ability of the…

As LLMs gain adoption in high-stakes domains like mental health, domain experts are increasingly consulted to provide input into policies governing their behavior. From an observation of 19 policymaking workshops with 9 experts over 15…

This paper studies the synthesis of control policies for an agent that has to satisfy a temporal logic specification in a partially observable environment, in the presence of an adversary. The interaction of the agent (defender) with the…

This study aims to address the pervasive challenge of quantifying uncertainty in large language models (LLMs) without logit-access. Conformal Prediction (CP), known for its model-agnostic and distribution-free features, is a desired…

Answering complex questions that require making latent decisions is a challenging task, especially when limited supervision is available. Recent works leverage the capabilities of large language models (LMs) to perform complex question…

Humans can reason compositionally when presented with new tasks. Previous research shows that appropriate prompting techniques enable large language models (LLMs) to solve artificial compositional generalization tasks such as SCAN. In this…

Traditional database access control mechanisms use role based methods, with generally row based and attribute based constraints for granularity, and privacy is achieved mainly by using views. However if only a set of views according to…