Related papers: DiSCTT: Consensus-Guided Self-Curriculum for Effic…

Large Language Models (LLMs) often exhibit strong linguistic abilities while remaining unreliable on multi-step reasoning tasks, particularly when deployed without additional training or fine-tuning. In this work, we study inference-time…

Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…

Scaling test-time compute via extended reasoning has become a key paradigm for improving the capabilities of large language models (LLMs). However, existing approaches optimize reasoning under fixed or uniformly sampled token budgets,…

Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most…

While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…

In the realm of Intelligent Tutoring System (ITS), the accurate assessment of students' knowledge states through Knowledge Tracing (KT) is crucial for personalized learning. However, due to data bias, $\textit{i.e.}$, the unbalanced…

Large language models (LLMs) exhibit enhanced reasoning at larger scales, driving efforts to distill these capabilities into smaller models via teacher-student learning. Previous works simply fine-tune student models on teachers' generated…

Large language models have demonstrated strong reasoning capabilities in general knowledge question answering. However, their ability to handle temporal information remains limited. To address this limitation, existing approaches often…

Captioning models are typically trained using the cross-entropy loss. However, their performance is evaluated on other metrics designed to better correlate with human assessments. Recently, it has been shown that reinforcement learning (RL)…

Although large language models (LLMs) have achieved remarkable performance across various tasks, they remain prone to errors. A key challenge is enabling them to self-correct. While prior research has relied on external tools or large…

While test-time scaling has enabled large language models to solve highly difficult tasks, state-of-the-art results come at exorbitant compute costs. These inefficiencies can be attributed to the miscalibration of post-trained language…

The underperformance of existing multimodal large language models for time series reasoning lies in the absence of rationale priors that connect temporal observations to their downstream outcomes, which leads models to rely on superficial…

Large language models (LLMs) now exhibit strong multi-step reasoning abilities, but existing inference-time scaling methods remain computationally expensive, often relying on extensive sampling or external evaluators. We propose a…

In this work we introduce a novel approach, based on sampling, for finding assignments that are likely to be solutions to stochastic constraint satisfaction problems and constraint optimisation problems. Our approach reduces the size of the…

Self-play with large language models has emerged as a promising paradigm for achieving self-improving artificial intelligence. However, existing self-play frameworks often suffer from optimization instability, due to (i) non-stationary…

Probabilistic decoding in Large Language Models (LLMs) often yields inconsistent outputs, particularly on complex or long-form questions. Self-Consistency (SC) mitigates this for short-form QA by majority voting over exact strings, whereas…

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Large reasoning models (LRMs) have exhibited strong performance on complex reasoning tasks, with further gains achievable through increased computational budgets at inference. However, current test-time scaling methods predominantly rely on…

We study self-distillation in settings where supervision is unreliable: there are no ground truth labels, verifiable rewards, or external graders to evaluate answers. We focus on document-grounded question answering with asymmetric context,…

Currently, pre-trained language models (PLMs) do not cope well with the distribution shift problem, resulting in models trained on the training set failing in real test scenarios. To address this problem, the test-time adaptation (TTA)…