Related papers: ReflectMT: Internalizing Reflection for Efficient …

Previous studies proposed that the reasoning capabilities of large language models (LLMs) can be improved through self-reflection, i.e., letting LLMs reflect on their own output to identify and correct mistakes in the initial responses.…

Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches…

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a…

Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficiency and accuracy:…

The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sentence to be translated can degrade translation quality. To…

Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency. Inspired by recent refinement-based approaches, we…

Freely Long-Thinking Transformer (FraiLT) is an improved transformer model designed to enhance processing capabilities without scaling up size. It utilizes a recursive approach, iterating over a subset of layers multiple times, and…

Large Reasoning Models (LRMs) achieve remarkable performance by explicitly generating multi-step chains of thought, but this capability incurs substantial inference latency and computational cost. Collaborative inference offers a promising…

Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation process is fragile; early token errors can cascade, which creates a clear need for…

In this paper, we propose a new metric for Machine Translation (MT) evaluation, based on bi-directional entailment. We show that machine generated translation can be evaluated by determining paraphrasing with a reference translation…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…

Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…

Recent advancements in Large Language Models (LLMs) have significantly improved their problem-solving capabilities. However, these models still struggle when faced with complex multi-step reasoning tasks. In this paper, we propose the…

We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback. This integrated…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning tasks, yet they often struggle with problems involving missing information, exhibiting issues such as incomplete responses, factual errors, and…

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks, sparking growing interest in their application to preference reasoning in recommendation systems. Existing methods typically…

Enhancing the reasoning capabilities of Large Language Models remains a critical challenge in artificial intelligence. We introduce RDoLT, Recursive Decomposition of Logical Thought prompting, a novel framework that significantly boosts LLM…

Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. One of these methods is…

Neural machine translation (NMT) is often criticized for failures that happen without awareness. The lack of competency awareness makes NMT untrustworthy. This is in sharp contrast to human translators who give feedback or conduct further…

Current reasoning paradigms for LLMs include chain-of-thought, ReAct, and post-hoc self-critique. These paradigms rely on two assumptions that fail on long-horizon, multi-stage tasks. As a result, errors accumulate silently across reasoning…