Although large reasoning models (LRMs) exhibit exceptional mathematical reasoning capabilities on clean inputs, their reasoning accuracy drops substantially in the presence of character-level noise such as typographical errors. Critically, their confidence estimates fail to reflect the corresponding decline in reasoning accuracy. While confidence calibration offers a principled solution, existing methods predominantly target clean inputs, leaving noisy scenarios largely unexplored. To address this gap, we propose DisCal (Distribution-aware Calibration), a confidence calibration framework for character-level noisy inputs. DisCal extracts uncertainty signals from both the empirical answer distribution and the model’s predictive distribution, and integrates them via a learned calibrator to produce well-calibrated confidence. Experiments across multiple mathematical reasoning benchmarks demonstrate that DisCal consistently outperforms existing calibration methods under noisy inputs, reducing Expected Calibration Error (ECE) by up to 39.21% and improving Area Under the Receiver Operating Characteristic Curve (AUROC) by up to 31.44%.

Open-domain timeline summarization (TLS) faces challenges from information overload and data sparsity when processing large-scale textual streams. Existing methods struggle to capture coherent event narratives due to fragmented descriptions and often accumulate noise through iterative retrieval strategies that lack effective relevance evaluation. This paper proposes: Reflective Retrieval-Augmented Timeline Summarization with Causal-Semantic Intergration, which offers a novel perspective for open-domain TLS by time point completion and event element completion. R2A-TLS establishes an initial retrieval, reflection, and deep retrieval system that reduces noise through a double filtering mechanism that iteratively generates a timeline for each text which passes the filtering. Then, the system reflects on the initial timeline with the aim of identifying information gaps through causal chain analysis and FrameNet based element validation. These gaps are reformulated into targeted queries to trigger deep retrieval for refining timeline coherence and density. Empirical evaluation on Open-TLS dataset reveals that our approach outperforms the best prior published approaches.

Entity linking (EL) focuses on accurately associating ambiguous mentions in text with corresponding entities in a knowledge graph. Traditional methods mainly rely on fine-tuning or training on specific datasets. However, they suffer from insufficient semantic comprehension, high training costs, and poor scalability. Large Language Models (LLMs) offer promising solutions for EL, but face key challenges: weak simple-prompt performance, costly fine-tuning, and limited recall and precision due to the lack of LLMs use in candidate generation. Building on this, we introduce a novel framework: Adaptive Entity Linking with LLM-Driven Contextualization. AELC, for the first time, introduces the combination of high-density key information condensation prompt and tool-invocation strategy, using a unified format semantic filtering strategy and an adaptive iterative retrieval mechanism to dynamically optimize the candidate set, significantly enhancing both precision and coverage. Furthermore, we innovatively reformulate the EL task as a multiple-choice problem, enabling multi-round reasoning to substantially improve the model’s discriminative capability and robustness. Experiments on four public benchmark datasets demonstrate that AELC achieves state-of-the-art performance. Further ablation studies validate the effectiveness of each module.

Large language models (LLMs) have achieved groundbreaking progress in Natural Language Processing (NLP). Despite the numerous advantages of LLMs, they also pose significant safety risks. Self-evaluation mechanisms have gained increasing attention as a key safeguard to ensure safe and controllable content generation. However, LLMs often exhibit overconfidence, which seriously compromises the accuracy of safety self-evaluation. To address this challenge, we propose SafeConf, a method to enhance the safety self-evaluation capability of LLMs through confidence calibration. The method performs semantic mutations on the original safety evaluation questions and adopts a self-consistency strategy to quantify confidence based on answer accuracy on the mutated questions. Finally, these confidence scores are used to construct a dataset for fine-tuning. We conducte experiments on both Chinese and English datasets. The results show that SafeConf improves self-evaluation accuracy by an average of 5.86% and 7.79% over the state-of-the-art baseline methods on Qwen2.5-7B-Instruct and Llama3-8B-Instruct models, respectively, without affecting the general capabilities of the models.

Large language models (LLMs) have achieved significant advances but can potentially generate harmful content such as social biases, extremism, and misinformation. Red teaming is a promising approach to enhance model safety by creating adversarial prompts to test and improve model robustness. However, existing red-teaming methods often require expensive fine-tuning, especially for large LLMs. We propose the Dynamic Evil Score-Guided Decoding framework (DESGD), an efficient red-teaming method that does not increase computational cost with the target model size. DESGD introduces the concept of an ‘evil score’ to dynamically evaluate the potential of tokens to contribute to harmful outputs during decoding. This framework constructs a small unsafe model using an adversarial dataset and adjusts the logits vector of the target model based on the evil score. Experiments show that DESGD achieves an ASR of 92.83% on the Llama-3.2-3B-Instruct model, compared to 83.48% with adversarial fine-tuning while using less computational resources. Similarly, on the Qwen2.5-3B-Instruct model, DESGD reaches an ASR of 88.62%, outperforming adversarial fine-tuning (77.56%).

Hate speech (HS) on social media exacerbates misinformation and baseless prejudices. Evidence-supported counterspeech (CS) is crucial for correcting misinformation and reducing prejudices through facts. Existing methods for generating evidence-supported CS often lack clear guidance with a core claim for organizing evidence and do not adequately address factuality and faithfulness hallucinations in CS within anti-hate contexts. In this paper, to mitigate the aforementioned, we propose F²RL, a Factuality and Faithfulness Reinforcement Learning framework for generating claim-guided and evidence-supported CS. Firstly, we generate counter-claims based on hate speech and design a self-evaluation mechanism to select the most appropriate one. Secondly, we propose a coarse-to-fine evidence retrieval method. This method initially generates broad queries to ensure the diversity of evidence, followed by carefully reranking the retrieved evidence to ensure its relevance to the claim. Finally, we design a reinforcement learning method with a triplet-based factuality reward model and a multi-aspect faithfulness reward model. The method rewards the generator to encourage greater factuality, more accurate refutation of hate speech, consistency with the claim, and better utilization of evidence. Extensive experiments on three benchmark datasets demonstrate that the proposed framework achieves excellent performance in CS generation, with strong factuality and faithfulness.

Nested named entity recognition (NER) is a task in which named entities may overlap with each other. Span-based approaches regard nested NER as a two-stage span enumeration and classification task, thus having the innate ability to handle this task. However, they face the problems of error propagation, ignorance of span boundary, difficulty in long entity recognition and requirement on large-scale annotated data. In this paper, we propose Extract-Select, a span selection framework for nested NER, to tackle these problems. Firstly, we introduce a span selection framework in which nested entities with different input categories would be separately extracted by the extractor, thus naturally avoiding error propagation in two-stage span-based approaches. In the inference phase, the trained extractor selects final results specific to the given entity category. Secondly, we propose a hybrid selection strategy in the extractor, which not only makes full use of span boundary but also improves the ability of long entity recognition. Thirdly, we design a discriminator to evaluate the extraction result, and train both extractor and discriminator with generative adversarial training (GAT). The use of GAT greatly alleviates the stress on the dataset size. Experimental results on four benchmark datasets demonstrate that Extract-Select outperforms competitive nested NER models, obtaining state-of-the-art results. The proposed model also performs well when less labeled data are given, proving the effectiveness of GAT.