Related papers: Compositional Multi-hop Factual Error Correction v…
Post-hoc explanation methods for machine learning models have been widely used to support decision-making. One of the popular methods is Counterfactual Explanation (CE), also known as Actionable Recourse, which provides a user with a…
Composition technologies improve reuse in the development of large-scale complex systems. Safety critical systems require intensive validation and verification activities. These activities should be compositional in order to reduce the…
Concurrent separation logic with fractional permissions (CSLPerm) provides a promising reasoning system to verify most complex sequential and concurrent fine-grained programs. The logic with strong and weak separating conjunctions offers a…
Structured claim decomposition is often proposed as a solution for verifying complex, multi-faceted claims, yet empirical results have been inconsistent. We argue that these inconsistencies stem from two overlooked bottlenecks: evidence…
This paper studies the problem of post-hoc calibration of machine learning classifiers. We introduce the following desiderata for uncertainty calibration: (a) accuracy-preserving, (b) data-efficient, and (c) high expressive power. We show…
For communication systems with heavy burst noise, an optimal Forward Error Correction (FEC) scheme is expected to have a large burst error correction capacity while simultaneously owning moderate random error correction capability. This…
Error Detection and Correction Codes (ECCs) are often used in digital designs to protect data integrity. Especially in safety-critical systems such as automotive electronics, ECCs are widely used and the verification of such complex logic…
Error Correction Codes (ECC) are fundamental to reliable digital communication, yet designing neural decoders that are both accurate and computationally efficient remains challenging. Recent denoising diffusion decoders achieve…
Faithfully correcting factual errors is critical for maintaining the integrity of textual knowledge bases and preventing hallucinations in sequence-to-sequence models. Drawing on humans' ability to identify and correct factual errors, we…
Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. However, in paragraph-level Chinese professional writing, linguistic (word/grammar/punctuation) and…
Quantum error correction (QEC) enables reliable computation on noisy hardware by encoding logical information across many physical qubits and periodically measuring parities to detect errors. A decoder is the classical algorithm that uses…
Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final…
Referring Expression Comprehension (REC) is a crucial cross-modal task that objectively evaluates the capabilities of language understanding, image comprehension, and language-to-image grounding. Consequently, it serves as an ideal testing…
Grammatical Error Correction (GEC) is the task of correcting errorful sentences into grammatically correct, semantically consistent, and coherent sentences. Popular GEC models either use large-scale synthetic corpora or use a large number…
As generated text becomes more commonplace, it is increasingly important to evaluate how well-supported such text is by external knowledge sources. Many approaches for evaluating textual support rely on some method for decomposing text into…
Decoders of quantum error correction (QEC) experiments make decisions based on detected errors and the expected rates of error events, which together comprise a detector error model. Here we show that the syndrome history of QEC experiments…
In this paper, we propose an iterative source error correction (ISEC) decoding scheme for deep-learning-based joint source-channel coding (Deep JSCC). Given a noisy codeword received through the channel, we use a Deep JSCC encoder and…
Automatic fact-checking has recently received more attention as a means of combating misinformation. Despite significant advancements, fact-checking systems based on retrieval-augmented language models still struggle to tackle adversarial…
Despite recent advances, vision-language models trained with standard contrastive objectives still struggle with compositional reasoning -- the ability to understand structured relationships between visual and linguistic elements. This…
Multi-hop QA benchmarks frequently reward Large Language Models (LLMs) for spurious correctness, masking ungrounded or flawed reasoning steps. To shift toward rigorous reasoning, we propose SAFE, a dynamic benchmarking framework that…