Related papers: NCV: A Node-Wise Consistency Verification Approach…

Cross-validation (CV) is a popular approach for assessing and selecting predictive models. However, when the number of folds is large, CV suffers from a need to repeatedly refit a learning procedure on a large number of training datasets.…

Recent studies have revealed the potential of training open-source Large Language Models (LLMs) to unleash LLMs' reasoning ability for enhancing vision-language navigation (VLN) performance, and simultaneously mitigate the domain gap…

Training large language models (LLMs) with chain-of-thought (CoT) supervision has proven effective for enhancing their reasoning abilities. However, obtaining reliable and accurate reasoning supervision remains a significant challenge. We…

Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy. Extended reasoning via chain-of-thought (CoT) prompting or…

Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a…

Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has focused on classifiers or short-form generation, confidence…

Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning trace might fail remains difficult. Confidence estimation…

Automatic misinformation detection performs well when deception is visible in what an article explicitly states. However, some misinformation articles remain locally coherent and only become misleading once compared with contemporaneous…

Multi-step reasoning improves the capabilities of large language models (LLMs) but increases the risk of errors propagating through intermediate steps. Process reward models (PRMs) mitigate this by scoring each step individually, enabling…

Recent advancements in Large Language Models (LLMs) have led to their widespread adoption in daily applications. Despite their impressive capabilities, they remain vulnerable to adversarial attacks, as even minor meaning-preserving changes…

Recent large vision-language models (LVLMs) can generate vision-text multimodal chain-of-thought (MCoT) traces after reinforcement fine-tuning (RFT). However, we observe that the visual information incorporated in MCoT is often inaccurate,…

Despite substantial advances in scaling test-time compute, an ongoing debate in the community is how it should be scaled up to enable continued and efficient improvements with scaling. There are largely two approaches: first, distilling…

Generative LLMs typically improve Named Entity Recognition (NER) performance through instruction tuning. They excel at generating entities by semantic pattern matching but lack an explicit, verifiable reasoning mechanism. This "cognitive…

According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language models (LLMs). However, in the multimodal (MM) domain, there is…

Entity matching is a fundamental task in data cleaning and data integration. With the rapid adoption of large language models (LLMs), recent studies have explored zero-shot and few-shot prompting to improve entity matching accuracy.…

Evaluating consistency in large language models (LLMs) is crucial for ensuring reliability, particularly in complex, multi-step interactions between humans and LLMs. Traditional self-consistency methods often miss subtle semantic changes in…

This paper presents novel techniques for improving the error correction performance and reducing the complexity of coarsely quantized 5G-LDPC decoders. The proposed decoder design supports arbitrary message-passing schedules on a…

Large language models are often assumed to acquire increasingly structured, generalizable internal representations simply by scaling data and parameters. We interrogate this assumption by introducing a Clinical Trial Natural Language…

Despite significant advancements, current large language models (LLMs) and vision-language models (LVLMs) continue to struggle with complex, multi-step, cross-modal common sense reasoning tasks, often exhibiting a lack of "deliberative…

Large Reasoning Models (LRMs) excel at complex tasks using Chain-of-Thought (CoT) reasoning. However, their tendency to overthinking leads to unnecessarily lengthy reasoning chains, dramatically increasing inference costs. To mitigate this…