相关论文: "My Answer is C": First-Token Probabilities Do Not…

Recent advancements in large language models (LLMs) have significantly advanced complex reasoning capabilities, particularly through extended chain-of-thought (CoT) reasoning that incorporates mechanisms such as backtracking,…

Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…

As large language models (LLMs) have grown in prevalence, particular benchmarks have become essential for the evaluation of these models and for understanding model capabilities. Most commonly, we use test accuracy averaged across multiple…

Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abundant works have been proposed to solve this problem with…

This paper examines how the sequencing of images and text within multi-modal prompts influences the reasoning performance of large language models (LLMs). We performed empirical evaluations using three commercial LLMs. Our results…

Instruction tuning aligns the response of large language models (LLMs) with human preferences. Despite such efforts in human--LLM alignment, we find that instruction tuning does not always make LLMs human-like from a cognitive modeling…

Large Vision-Language Models (LVLMs) have achieved strong performance on vision-language tasks, particularly Visual Question Answering (VQA). While prior work has explored unimodal biases in VQA, the problem of selection bias in…

In-context learning (ICL) has emerged as an effective solution for few-shot learning with large language models (LLMs). However, how LLMs leverage demonstrations to specify a task and learn a corresponding computational function through ICL…

LLM confidence calibration is often evaluated by comparing two signals: token-probability scores and verbalized confidence. These signals are sometimes treated as direct readouts of model uncertainty, but their comparison depends on…

Multiple choice question answering (MCQA) is popular for LLM evaluation due to its simplicity and human-like testing, but we argue for its reform. We first reveal flaws in MCQA's format, as it struggles to: 1) test generation/subjectivity;…

Benchmarks have emerged as the central approach for evaluating Large Language Models (LLMs). The research community often relies on a model's average performance across the test prompts of a benchmark to evaluate the model's performance.…

While large language models (LLMs) like GPT-3 have achieved impressive results on multiple choice question answering (MCQA) tasks in the zero, one, and few-shot settings, they generally lag behind the MCQA state of the art (SOTA). MCQA…

Large Language Models (LLMs) are increasingly used to answer everyday questions, yet their performance on culturally grounded and dialectal content remains uneven across languages. We propose a comprehensive method that (i) translates…

While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority…

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…

State-of-the-art Large Language Models (LLMs) are accredited with an increasing number of different capabilities, ranging from reading comprehension, over advanced mathematical and reasoning skills to possessing scientific knowledge. In…

Multimodal Large Language Models (MLLM) classification performance depends critically on evaluation protocol and ground truth quality. Studies comparing MLLMs with supervised and vision-language models report conflicting conclusions, and we…

Large language models (LLM) have revolutionized the processing of natural language. Although first benchmarks of the process modeling abilities of LLM are promising, it is currently under debate to what extent an LLM can generate good…

We present an empirical evaluation of various outputs generated by nine of the most widely-available large language models (LLMs). Our analysis is done with off-the-shelf, readily-available tools. We find a correlation between percentage of…

As large language models (LLMs) become increasingly integrated into society, their alignment with human morals is crucial. To better understand this alignment, we created a large corpus of human- and LLM-generated responses to various moral…