Related papers: Think before you speak: Training Language Models W…
Language models (LMs) are pre-trained on raw text datasets to generate text sequences token-by-token. While this approach facilitates the learning of world knowledge and reasoning, it does not explicitly optimize for linguistic competence.…
Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show…
Large Language Models (LLMs) excel at reasoning and planning when trained on chainof-thought (CoT) data, where the step-by-step thought process is explicitly outlined by text tokens. However, this results in lengthy inputs where many words…
To generate coherent responses, language models infer unobserved meaning from their input text sequence. One potential explanation for this capability arises from theories of delay embeddings in dynamical systems, which prove that…
Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…
While there is much recent interest in studying why Transformer-based large language models make predictions the way they do, the complex computations performed within each layer have made their behavior somewhat opaque. To mitigate this…
When a language model generates text, the selection of individual tokens might lead it down very different reasoning paths, making uncertainty difficult to quantify. In this work, we consider whether reasoning language models represent the…
Why do thinking language models like DeepSeek R1 outperform their base counterparts? Despite consistent performance gains, it remains unclear to what extent thinking models learn entirely new reasoning capabilities or repurpose pre-existing…
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…
Next-token prediction serves as the dominant component in current neural language models. During the training phase, the model employs teacher forcing, which predicts tokens based on all preceding ground truth tokens. However, this approach…
Language models typically need to be trained or finetuned in order to acquire new knowledge, which involves updating their weights. We instead envision language models that can simply read and memorize new data at inference time, thus…
Simultaneous machine translation consists in starting output generation before the entire input sequence is available. Wait-k decoders offer a simple but efficient approach for this problem. They first read k source tokens, after which they…
The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…
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…
Reasoning-oriented language models typically expose explicit reasoning as a long, front-loaded chain of "thinking" tokens before the main output, either always enabled or externally toggled at inference time. Although this can help on…
Humans can approach complex visual problems by mentally simulating intermediate visual steps, rather than reasoning through language alone. Inspired by this, several works on Vision-Language Models have recently explored chain-of-thought…
Most language model pre-training frameworks concatenate multiple documents into fixed-length sequences and use causal masking to compute the likelihood of each token given its context; this strategy is widely adopted due to its simplicity…
Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. Cascading offers a simple strategy to achieve more favorable cost-quality…
Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…
Reasoning is essential for effective communication and decision-making. While recent advances in LLMs and MLLMs have shown that incorporating explicit reasoning significantly improves understanding and generalization, reasoning in LSMs…