Related papers: Is my model perplexed for the right reason? Contra…

People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are trained to predict the next token solely from text input, not underlying intent. Because written…

Padding tokens are widely used in large language models (LLMs) to equalize sequence lengths during batched inference. While they should be fully masked, implementation errors can cause them to influence computation, and the extent of this…

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…

The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes. In this paper, we present an alternative approach, concentrating on the quality of LM…

Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…

Language models can be prompted to perform a wide variety of zero- and few-shot learning problems. However, performance varies significantly with the choice of prompt, and we do not yet understand why this happens or how to pick the best…

Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to what extent such scores truly reflect reliance on visual evidence. Motivated by a surprising…

Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects…

Large language models (LLMs) are increasingly deployed as conversational assistants in open-domain, multi-turn settings, where users often provide incomplete or ambiguous information. However, existing LLM-focused clarification benchmarks…

In this paper, we explore the potential of Large Language Models (LLMs) with assertions to mitigate imbalances in educational datasets. Traditional models often fall short in such contexts, particularly due to the complexity and nuanced…

This paper surveys evaluation techniques to enhance the trustworthiness and understanding of Large Language Models (LLMs). As reliance on LLMs grows, ensuring their reliability, fairness, and transparency is crucial. We explore algorithmic…

Large language model (LLM) evaluations often assume there is a single correct response -- a gold label -- for each item in the evaluation corpus. However, some tasks can be ambiguous -- i.e., they provide insufficient information to…

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…

A novel hack involving Large Language Models (LLMs) has emerged, exploiting adversarial suffixes to deceive models into generating perilous responses. Such jailbreaks can trick LLMs into providing intricate instructions to a malicious user…

Benchmarks underpin how progress in large language models (LLMs) is measured and trusted. Yet our analyses reveal that apparent convergence in benchmark accuracy can conceal deep epistemic divergence. Using two major reasoning benchmarks -…

Current evaluation metrics for language modeling and generation rely heavily on the accuracy of predicted (or generated) words as compared to a reference ground truth. While important, token-level accuracy only captures one aspect of a…

When deploying large language models (LLMs), it is important to ensure that these models are not only capable, but also reliable. Many benchmarks have been created to track LLMs' growing capabilities, however there has been no similar focus…

Transformer language models have received widespread public attention, yet their generated text is often surprising even to NLP researchers. In this survey, we discuss over 250 recent studies of English language model behavior before…

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

The widespread adoption of large language models (LLMs) makes it important to recognize their strengths and limitations. We argue that in order to develop a holistic understanding of these systems we need to consider the problem that they…