Fixed-target backdoor attacks can silently hijack the outputs of large language models by driving models to generate attacker-specified sequences upon trigger activation, motivating lightweight inference-time detection. Recent defenses like ConfGuard, which we term Local-window Confidence Detectors, leverage sliding windows to identify local spans where the top-1 probability, referred to as token confidence, exceeds 0.99 as indicators of backdoor activation. However, benign deterministic tasks such as math reasoning can exhibit similar sustained high-confidence patterns, causing confidence conflation. On the GSM8K dataset, ConfGuard’s default settings yield a 72.89% false positive rate, causing substantial over-defense. Our empirical analysis reveals that benign deterministic generation exhibits sparse confidence "dips", whereas backdoor-triggered generation forms a sustained high-confidence "plateau". Building on this, we propose RatioGuard, which utilizes a global high-confidence token ratio computed over the generated prefix to address confidence conflation. Across models and datasets, RatioGuard reduces false positives by up to 71.57 percentage points over ConfGuard while maintaining over 99% true positive rate with 1.005× runtime latency.

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.

Extracting event causality underlies a broad spectrum of natural language processing applications. Cutting-edge methods break this task into Event Detection and Event Causality Identification. Although the pipelined solutions succeed in achieving acceptable results, the inherent nature of separating the task incurs limitations. On the one hand, it suffers from the lack of cross-task dependencies and may cause error propagation. On the other hand, it predicts events and relations separately, undermining the integrity of the event causality graph (ECG). To address such issues, in this paper, we propose an approach for Structure-Aware Event Causality Generation (SEAG). With a graph linearization module, we generate the ECG structure in a way of text2text generation based on a pre-trained language model. To foster the structural representation of the ECG, we introduce the novel Causality Structural Discrimination training paradigm in which we perform structural discriminative training alongside auto-regressive generation enabling the model to distinguish from constructed incorrect ECGs. We conduct experiments on three datasets. The experimental results demonstrate the effectiveness of structural event causality generation and the causality structural discrimination training.