Related papers: Language Model Cascades: Token-level uncertainty a…

Generative Language Models rely on autoregressive decoding to produce the output sequence token by token. Many tasks such as preference optimization, require the model to produce task-level output consisting of multiple tokens directly by…

Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. These compositions are…

Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any…

The emergence of discourse-like tokens such as "wait" and "therefore" in large language models (LLMs) has offered a unique window into their reasoning processes. However, systematic analyses of how such signals vary across training…

Decoding strategies manipulate the probability distribution underlying the output of a language model and can therefore affect both generation quality and its uncertainty. In this study, we investigate the impact of decoding strategies on…

Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…

Extracting sentence embeddings from large language models (LLMs) is a promising direction, as LLMs have demonstrated stronger semantic understanding capabilities. Previous studies typically focus on prompt engineering to elicit sentence…

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…

Language models are often trained to maximize the likelihood of the next token given past tokens in the training dataset. However, during inference time, they are utilized differently, generating text sequentially and auto-regressively by…

Several previous works concluded that the largest part of generation capabilities of large language models (LLM) are learned (early) during pre-training. However, LLMs still require further alignment to adhere to downstream task…

Large language models (LLMs) process and predict sequences containing text to answer questions, and address tasks including document summarization, providing recommendations, writing software and solving quantitative problems. We provide a…

Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to…

Language models have consistently grown to compress more world knowledge into their parameters, but the knowledge that can be pretrained into them is upper-bounded by their parameter size. Especially the capacity of Small Language Models…

Large Language Models (LLMs) excel at generating fluent text but struggle to enforce external constraints because they generate tokens sequentially without explicit control mechanisms. GenCP addresses this limitation by combining LLM…

The availability of a wide range of large language models (LLMs) embedded in various agentic systems has significantly increased the potential of model selection strategies to improve the cost-performance tradeoff. Existing strategies…

A challenge in human-AI decision-making is to balance three factors: the correctness of predictions, the cost of knowledge and reasoning complexity, and the confidence about whether to abstain from automated answers or escalate to human…

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks. However, the truthfulness of their outputs is not guaranteed, and their tendency toward overconfidence further limits reliability. Uncertainty…

Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the…

Learning to predict masked tokens in a sequence has been shown to be a helpful pretraining objective for powerful language models such as PaLM2. After training, such masked language models (MLMs) can provide distributions of tokens in the…