Related papers: Extending RECAST for Truth-Level Reinterpretations

This paper presents an efficient multi-scale vision Transformer, called ResT, that capably served as a general-purpose backbone for image recognition. Unlike existing Transformer methods, which employ standard Transformer blocks to tackle…

The Scene Representation Transformer (SRT) is a recent method to render novel views at interactive rates. Since SRT uses camera poses with respect to an arbitrarily chosen reference camera, it is not invariant to the order of the input…

Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, prior work has not explored how these methods can be…

Large language model editing methods frequently suffer from overfitting, wherein factual updates can propagate beyond their intended scope, overemphasizing the edited target even when it's contextually inappropriate. To address this…

Finetuning language agents with reasoning-action trajectories is effective, but obtaining these trajectories from human annotations or stronger models is costly and sometimes impractical. In this paper, we investigate the use of…

Recent Large Reasoning Models (LRMs) have achieved remarkable progress on task-specific benchmarks, yet their evaluation methods remain constrained by isolated problem-solving paradigms. Existing benchmarks predominantly assess…

In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components,…

This paper introduces reAnalyst, a framework designed to facilitate the study of reverse engineering (RE) practices through the semi-automated annotation of RE activities across various RE tools. By integrating tool-agnostic data collection…

Large Language Models (LLMs) have made substantial progress in recent years, yet evaluating their capabilities in practical Retrieval-Augmented Generation (RAG) scenarios remains challenging. In practical applications, LLMs must demonstrate…

Retrieval-Augmented Language Models (RALMs) face significant challenges in reducing factual errors, particularly in document relevance evaluation and knowledge integration. We introduce a framework for structured relevance assessment that…

Traditional session types prescribe bidirectional communication protocols for concurrent computations, where well-typed programs are guaranteed to adhere to the protocols. However, simple session types cannot capture properties beyond the…

Code summarization aims to generate concise natural language descriptions of source code, which can help improve program comprehension and maintenance. Recent studies show that syntactic and structural information extracted from abstract…

Although Large Language Models (LLMs) have demonstrated extraordinary capabilities in many domains, they still have a tendency to hallucinate and generate fictitious responses to user requests. This problem can be alleviated by augmenting…

Large language models have achieved remarkable success but remain largely black boxes with poorly understood internal mechanisms. To address this limitation, many researchers have proposed various interpretability methods including…

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

Unsupervised learning of low-dimensional, semantic representations of words and entities has recently gained attention. In this paper we describe the Semantic Entity Retrieval Toolkit (SERT) that provides implementations of our previously…

Simultaneous speech-to-text translation (SimulST) translates source-language speech into target-language text concurrently with the speaker's speech, ensuring low latency for better user comprehension. Despite its intended application to…

The widespread adoption of REST APIs, coupled with their growing complexity and size, has led to the need for automated REST API testing tools. Current tools focus on the structured data in REST API specifications but often neglect valuable…

Leveraging sensing modalities across diverse spatial and temporal resolutions can improve performance of robotic manipulation tasks. Multi-spatial resolution sensing provides hierarchical information captured at different spatial scales and…

Transfer learning uses a data model, trained to make predictions or inferences on data from one population, to make reliable predictions or inferences on data from another population. Most existing transfer learning approaches are based on…