相关论文: Dynamic Evaluation for Oversensitivity in LLMs

Large language models (LLMs) have witnessed rapid advancements, demonstrating remarkable capabilities. However, a notable vulnerability persists: LLMs often uncritically accept flawed or contradictory premises, leading to inefficient…

Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce BeyondBench, an evaluation framework using algorithmic…

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Large language models (LLMs) are increasingly used as decision-support tools in data-constrained scientific workflows, where correctness and validity are critical. However, evaluation practices often emphasize stability or reproducibility…

Despite the remarkable advances of Large Language Models (LLMs) across diverse cognitive tasks, the rapid enhancement of these capabilities also introduces emergent deceptive behaviors that may induce severe risks in high-stakes…

Vision-language models (VLMs) have made significant progress in recent visual-question-answering (VQA) benchmarks that evaluate complex visio-linguistic reasoning. However, are these models truly effective? In this work, we show that VLMs…

Multilingual large language models (LLMs) are advancing rapidly, with new models frequently claiming support for an increasing number of languages. However, existing evaluation datasets are limited and lack cross-lingual alignment, leaving…

Large Language Models (LLMs) have become instrumental across various applications, with the customization of these models to specific scenarios becoming increasingly critical. System message, a fundamental component of LLMs, is consist of…

We introduce OVERTONBENCH, a novel framework for measuring Overton pluralism in LLMs--the extent to which diverse viewpoints are represented in model outputs. We (i) formalize Overton pluralism as a set coverage metric (OVERTONSCORE), (ii)…

Evaluating Large Language Models' (LLMs) anthropomorphic capabilities has become increasingly important in contemporary discourse. Utilizing the emotion appraisal theory from psychology, we propose to evaluate the empathy ability of LLMs,…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically…

The advancement of Large Language Models (LLMs) has raised concerns regarding their dual-use potential in cybersecurity. Existing evaluation frameworks overwhelmingly focus on Information Technology (IT) environments, failing to capture the…

Evaluating large language models (LLMs) on question answering often relies on static benchmarks that reward memorization and understate the role of retrieval, failing to capture the dynamic nature of world knowledge. We present…

It is unclear whether strong forecasting performance reflects genuine temporal understanding or the ability to reason under contextual and event-driven conditions. We introduce TemporalBench, a multi-domain benchmark designed to evaluate…

The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval. However, these systems are vulnerable to adversarial attacks, especially ranking manipulation attacks,…

Given the increasing use of synthetic data in language model (LM) post-training, an LM's ability to generate high-quality data has become nearly as crucial as its ability to solve problems directly. While prior works have focused on…

Large Language Models (LLMs) are pretrained on textual data up to a specific temporal cutoff. This creates a strict knowledge boundary beyond which models cannot provide accurate information without querying external sources. More subtly,…

Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appropriate underlying mechanisms and risking confirmation bias. We introduce a simple,…

Despite the widespread application of Large Language Models (LLMs) across various domains, they frequently exhibit overconfidence when encountering uncertain scenarios, yet existing solutions primarily rely on evasive responses (e.g., "I…