相关论文: Factual Self-Awareness in Language Models: Represe…

In-context learning \ -- performing tasks based on examples given in the prompt \ -- is an important capability that has emerged in large language models and has received significant attention in both theory and practice. Existing…

We study whether Large Language Models (LLMs) inherently capture domain-specific nuances in natural language. Our experiments probe the domain sensitivity of LLMs by examining their ability to distinguish queries from different domains…

Multilingual large language models (LLMs) are expected to recall factual knowledge consistently across languages. However, the factors that give rise to such crosslingual consistency -- and its frequent failure -- remain poorly understood.…

In recent years, several Speech Language Models (SLMs) that represent speech and written text jointly have been presented. The question then emerges about how model-internal mechanisms are similar and different when operating in the two…

Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex cognitive tasks. However, their complexity and lack of transparency have raised several trustworthiness concerns, including the propagation of…

The veracity of a factoid is largely independent of the language it is written in. However, language models are inconsistent in their ability to answer the same factual question across languages. This raises questions about how LLMs…

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Despite demonstrating remarkable performance across a wide range of tasks, large language models (LLMs) have also been found to frequently produce outputs that are incomplete or selectively omit key information. In sensitive domains, such…

Despite showing increasingly human-like abilities, large language models (LLMs) often struggle with factual inaccuracies, i.e. "hallucinations", even when they hold relevant knowledge. To address these hallucinations, current approaches…

Large language models (LLMs) have recently driven striking performance improvements across a range of natural language processing tasks. The factual knowledge acquired during pretraining and instruction tuning can be useful in various…

When a language model is fed a wrong answer, what happens inside the network? Current understanding treats truthfulness as a static property of individual-layer representations-a direction to be probed, a feature to be extracted. Less is…

Despite their impressive performance on diverse tasks, large language models (LMs) still struggle with tasks requiring rich world knowledge, implying the limitations of relying solely on their parameters to encode a wealth of world…

Automated fact-checking, using machine learning to verify claims, has grown vital as misinformation spreads beyond human fact-checking capacity. Large Language Models (LLMs) like GPT-4 are increasingly trusted to write academic papers,…

Pretrained language models (LMs) are susceptible to generate text with nonfactual information. In this work, we measure and improve the factual accuracy of large-scale LMs for open-ended text generation. We design the FactualityPrompts test…

Inverse tasks can uncover potential reasoning gaps as Large Language Models (LLMs) scale up. In this work, we explore the redefinition task, in which we assign alternative values to well-known physical constants and units of measure,…

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…

Large language models (LLMs) generate fluent and complex outputs but often fail to recognize their own mistakes and hallucinations. Existing approaches typically rely on external judges, multi-sample consistency, or text-based…

To collaborate effectively with humans, language models must be able to explain their decisions in natural language. We study a specific type of self-explanation: self-generated counterfactual explanations (SCEs), where a model explains its…

Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We show that when personalized LLMs face factual queries,…

Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual representations within these models, it remains unclear whether they functionally rely on…