相关论文: Before you <think>, monitor: Implementing Flavell'…

Test-time reasoning architectures such as those following the Generate-Verify paradigm, where a model iteratively refines or verifies its own generated outputs, prioritise generation and verification but exclude the monitoring processes…

Large Language Models (LLMs) demonstrate strong reasoning performance, yet their ability to reliably monitor, diagnose, and correct their own errors remains limited. We introduce a psychologically grounded metacognitive framework that…

Self-detection for Large Language Models (LLMs) seeks to evaluate the trustworthiness of the LLM's output by leveraging its own capabilities, thereby alleviating the issue of output hallucination. However, existing self-detection approaches…

Fact-seeking question answering with large language models (LLMs) remains unreliable when answers depend on up-to-date or conflicting information. Although retrieval-augmented and tool-using LLMs reduce hallucinations, they often rely on…

Self-consistency methods are the core technique for improving the reasoning reliability of multimodal large language models (MLLMs). By generating multiple reasoning results through repeated sampling and selecting the best answer via…

Recent advances in Large Language Models (LLMs) have shown impressive capabilities in various applications, yet LLMs face challenges such as limited context windows and difficulties in generalization. In this paper, we introduce a…

Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates…

Self-improvement is a mechanism in Large Language Model (LLM) pre-training, post-training and test-time inference. We explore a framework where the model verifies its own outputs, filters or reweights data based on this verification, and…

This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine…

Self-reflection -- the ability of a large language model (LLM) to revisit, evaluate, and revise its own reasoning -- has recently emerged as a powerful behavior enabled by reinforcement learning with verifiable rewards (RLVR). While…

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on…

In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…

Vision-Language Models (VLMs) have recently shown promising advancements in sequential decision-making tasks through task-specific fine-tuning. However, common fine-tuning methods, such as Supervised Fine-Tuning (SFT) and Reinforcement…

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:…

This work studies improving large language model (LLM) generations at inference time by mitigating fact-conflicting hallucinations. Particularly, we propose a self-endorsement framework that leverages the fine-grained fact-level comparisons…

Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely…

The Metacognitive Probe is an exploratory five-task, 15-slot diagnostic that decomposes an LLM's confidence behaviour into five behaviourally-distinct dimensions: confidence calibration (T1-CC), epistemic vigilance (T2-EV), knowledge…

Vision-Language Models (VLMs) exhibit significant performance plateaus in specialized domains like precision agriculture, primarily due to "Reasoning-Driven Hallucination" where linguistic priors override visual perception. A key bottleneck…

Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in areas such as math and coding. With a long context length, LLMs…

Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…