Related papers: Does Slightly Mean Somewhat? Measuring Vague Inten…
This study addresses a series of methodological questions that arise when modeling inflectional morphology with Linear Discriminative Learning. Taking the semi-productive German noun system as example, we illustrate how decisions made about…
Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these…
Large reasoning models (LRMs) sometimes note in their chain of thought (CoT) that they may be under evaluation. Researchers worry that this verbalised evaluation awareness (VEA) causes models to adapt their outputs strategically, optimising…
Common Large Language model (LLM) evaluations rely on demonstration examples to steer models' responses to the desired style. While the number of examples used has been studied and standardized, the choice of how to format examples is less…
Large Language Models are affected by the phenomena of memorizing and forgetting their training data. But how do these vary by model size? We work towards this question by investigating how the model size affects the model's ability to…
To address the challenge of quantifying uncertainty in the outputs generated by language models, we propose a novel measure of semantic uncertainty, semantic spectral entropy, that is statistically consistent under mild assumptions. This…
As LLMs reduce English-centric bias, a surprising trend emerges: non-English responses sometimes outperform English on reasoning tasks. We hypothesize that language functions as a latent variable that structurally modulates the model's…
Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principled interventions at three levels: prompts, activations, and…
Vector space models of word meaning all share the assumption that words occurring in similar contexts have similar meanings. In such models, words that are similar in their topical associations but differ in their logical force tend to…
Large language models (LLMs) are widely used for tasks ranging from summarisation to decision support. In practice, identical prompts do not always produce identical outputs, even when temperature and other decoding parameters are fixed. In…
As large language models are increasingly deployed in retrieval-augmented generation and agentic systems that accumulate extensive context, understanding how distracting information affects long-context performance becomes critical. Prior…
Lexical-syntactic flexibility, in the form of conversion (or zero-derivation) is a hallmark of English morphology. In conversion, a word with one part of speech is placed in a non-prototypical context, where it is coerced to behave as if it…
Recent works have shown a surprising result: a small fraction of Large Language Model (LLM) parameter outliers are disproportionately important to the quality of the model. LLMs contain billions of parameters, so these small fractions, such…
Today's probabilistic language generators fall short when it comes to producing coherent and fluent text despite the fact that the underlying models perform well under standard metrics, e.g., perplexity. This discrepancy has puzzled the…
Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion…
A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…
We observe an empirical phenomenon in Large Language Models (LLMs) -- very few activations exhibit significantly larger values than others (e.g., 100,000 times larger). We call them massive activations. First, we demonstrate the widespread…
Verbal confidence elicitation is widely used to extract uncertainty estimates from LLMs. We tested whether seven instruction-tuned open-weight models (3-9B parameters, four families) produce verbalised confidence that meets minimal validity…
While zero-shot instructional prompts like "Let's think step-by-step" have revolutionized Large Language Model performance, a fundamental question remains unanswered: which specific words drive their remarkable effectiveness? We introduce…
As large language models (LLMs) are increasingly deployed as automated graders in educational settings, concerns about fairness and bias in their evaluations have become critical. This study investigates whether LLMs exhibit implicit…