相关论文: Characterizing Mechanisms for Factual Recall in La…

The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills. Are these skills general and transferable, or specialized to specific tasks seen during…

Counterfactuals refer to minimally edited inputs that cause a model's prediction to change, serving as a promising approach to explaining the model's behavior. Large language models (LLMs) excel at generating English counterfactuals and…

Pretrained Language Models (LMs) have demonstrated ability to perform numerical reasoning by extrapolating from a few examples in few-shot settings. However, the extent to which this extrapolation relies on robust reasoning is unclear. In…

Modern language models can imitate complex patterns through few-shot learning, enabling them to complete challenging tasks without fine-tuning. However, imitation can also lead models to reproduce inaccuracies or harmful content if present…

Understanding how Transformer-based language models store and retrieve factual associations is critical for improving interpretability and enabling targeted model editing. Prior work, primarily on GPT-style models, has identified MLP…

We study reasoning for accessing world knowledge stored in a language model's parameters. For example, recalling that Canberra is Australia's capital may benefit from thinking through major cities and the concept of purpose-built capitals.…

Large language models (LLMs) generate fluent text across a wide range of tasks, but the fabrication of non-existent academic citations remains a critical and well-documented failure mode. Building on prior work that frames hallucination and…

Graphs data is crucial for many applications, and much of it exists in the relations described in textual format. As a result, being able to accurately recall and encode a graph described in earlier text is a basic yet pivotal ability that…

Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to over-reliance on memorized training examples. However, the…

Large language models (LLMs) are increasingly used for causal and counterfactual reasoning, yet their reliability in real-world policy evaluation remains underexplored. We construct a benchmark of 40 empirical policy evaluation cases drawn…

Large language models (LLMs) have demonstrated remarkable progress in leveraging diverse knowledge sources. This study investigates how nine widely used LLMs allocate knowledge between local context and global parameters when answering…

Counterfactual reasoning is widely recognized as one of the most challenging and intricate aspects of causality in artificial intelligence. In this paper, we evaluate the performance of large language models (LLMs) in counterfactual…

Transformer-based language models (LMs) are known to capture factual knowledge in their parameters. While previous work looked into where factual associations are stored, only little is known about how they are retrieved internally during…

Multilingual large language models (LLMs) offer promising opportunities for cross-lingual information access, yet their use of factual knowledge remains highly sensitive to the input language. Prior work has addressed this through English…

Large language models (LLMs) exhibit remarkable capabilities in question answering and reasoning thanks to their extensive parametric memory. However, their knowledge is inherently limited by the scope of their pre-training data, while…

Large language models (LLMs) have performed well on several reasoning benchmarks, including ones that test analogical reasoning abilities. However, it has been debated whether they are actually performing humanlike abstract reasoning or…

Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A…

Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In this paper, toward identifying guidelines for mitigating this…

Factual incorrectness in generated content is one of the primary concerns in ubiquitous deployment of large language models (LLMs). Prior findings suggest LLMs can (sometimes) detect factual incorrectness in their generated content (i.e.,…

Large Language Models (LLMs) can produce verbalized self-explanations, yet prior studies suggest that such rationales may not reliably reflect the model's true decision process. We ask whether these explanations nevertheless help users…