Large language models (LLMs) have demonstrated impressive capabilities in
storing and recalling factual knowledge, but also in adapting to novel
in-context information. Yet, the mechanisms underlying their in-context
grounding remain unknown, especially in situations where in-context information
contradicts factual knowledge embedded in the parameters. This is critical for
retrieval-augmented generation methods, which enrich the context with
up-to-date information, hoping that grounding can rectify the outdated
parametric knowledge. In this study, we introduce Fakepedia, a counterfactual
dataset designed to evaluate grounding abilities when the parametric knowledge
clashes with the in-context information. We benchmark various LLMs with
Fakepedia and discover that GPT-4-turbo has a strong preference for its
parametric knowledge. Mistral-7B, on the contrary, is the model that most
robustly chooses the grounded answer. Then, we conduct causal mediation
analysis on LLM components when answering Fakepedia queries. We demonstrate
that inspection of the computational graph alone can predict LLM grounding with
92.8% accuracy, especially because few MLPs in the Transformer can predict
non-grounded behavior. Our results, together with existing findings about
factual recall mechanisms, provide a coherent narrative of how grounding and
factual recall mechanisms interact within LLMs.

中文摘要：本研究介绍了 Fakepedia，一个反事实数据集，用于评估大型语言模型在参数化知识与上下文信息相冲突时的接地能力。我们测试了各种大型语言模型在 Fakepedia 上的表现，并发现 GPT-4-turbo 更偏好参数化知识，而 Mistral-7B 则最稳定地选择了接地答案。此外，我们对大型语言模型进行因果中介分析，结果表明仅凭计算图的检查即可预测 92.8% 准确度的接地情况，尤其是变压器中的少数 MLP 可以预测非接地行为。我们的结果与现有关于事实回忆机制的发现相结合，提供了大型语言模型中接地和事实回忆机制的相互作用的连贯叙述。

定位和检测语言模型基础的瑕疵：使用 Fakepedia

A Glitch in the Matrix? Locating and Detecting Language Model Grounding  with Fakepedia

Video Temporal Grounding (VTG), which aims to ground target clips from videos
(such as consecutive intervals or disjoint shots) according to custom language
queries (e.g., sentences or words), is key for video browsing on social media.
Most methods in this direction develop taskspecific models that are trained
with type-specific labels, such as moment retrieval (time interval) and
highlight detection (worthiness curve), which limits their abilities to
generalize to various VTG tasks and labels. In this paper, we propose to Unify
the diverse VTG labels and tasks, dubbed UniVTG, along three directions:
Firstly, we revisit a wide range of VTG labels and tasks and define a unified
formulation. Based on this, we develop data annotation schemes to create
scalable pseudo supervision. Secondly, we develop an effective and flexible
grounding model capable of addressing each task and making full use of each
label. Lastly, thanks to the unified framework, we are able to unlock temporal
grounding pretraining from large-scale diverse labels and develop stronger
grounding abilities e.g., zero-shot grounding. Extensive experiments on three
tasks (moment retrieval, highlight detection and video summarization) across
seven datasets (QVHighlights, Charades-STA, TACoS, Ego4D, YouTube Highlights,
TVSum, and QFVS) demonstrate the effectiveness and flexibility of our proposed
framework. The codes are available at this https URL

通过统一视频时序定位（Video Temporal Grounding）的各种标签和任务，提出的 UniVTG 框架在大规模不同标签下能够解锁时序定位预训练，并获得更强的定位能力，例如零样本时序定位。对三项任务（时间区间提取、重要片段检测和视频摘要）在七个数据集上的广泛实验证明了该框架的有效性和灵活性。