Related papers: Exploring the LLM Journey from Cognition to Expres…
We consider Representation Misdirection (RM), a class of large language model (LLM) unlearning methods that achieve forgetting by redirecting the forget-representations, that is, latent representations of forget-samples, toward a target…
Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to over-reliance on memorized training examples. However, the…
Cognition and language seem closely related to the human cognitive process, although they have not been studied and investigated in detail. Our brain is too complex to fully comprehend the structures and connectivity, as well as its…
The surprising ability of Large Language Models (LLMs) to perform well on complex reasoning with only few-shot chain-of-thought prompts is believed to emerge only in very large-scale models (100+ billion parameters). We show that such…
Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions…
Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this…
We examine the language capabilities of language models (LMs) from the critical perspective of human language acquisition. Building on classical language development theories, we propose a three-stage framework to assess the abilities of…
Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the…
Understanding the inner workings of Large Language Models (LLMs) is a critical research frontier. Prior research has shown that a single LLM's concept representations can be captured as steering vectors (SVs), enabling the control of LLM…
Human problem-solving is enriched by a diversity of styles and personality traits, yet the development of Large Language Models (LLMs) has largely prioritized uniform performance benchmarks that favour specific behavioural tendencies such…
Large Language Models (LLMs) achieve impressive performance in a wide range of tasks, even if they are often trained with the only objective of chatting fluently with users. Among other skills, LLMs show emergent abilities in mathematical…
Understanding whether large language models (LLMs) and the human brain converge on similar computational principles remains a fundamental and important question in cognitive neuroscience and AI. Do the brain-like patterns observed in LLMs…
In recent years, training methods centered on Reinforcement Learning (RL) have markedly enhanced the reasoning and alignment performance of Large Language Models (LLMs), particularly in understanding human intents, following user…
Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we…
Reinforcement learning (RL) has been applied to improve large language model (LLM) reasoning, yet the systematic study of how training scales with task difficulty has been hampered by the lack of controlled, scalable environments. Observed…
Logical reasoning serve as a central capability in LLMs and includes three main forms: deductive, inductive, and abductive reasoning. In this work, we study the knowledge representations of these reasoning types in LLMs and analyze the…
This paper studies the emergence of interpretable categorical features within large language models (LLMs), analyzing their behavior across training checkpoints (time), transformer layers (space), and varying model sizes (scale). Using…
Large Language Models (LLMs) have been applied to automate cyber security activities and processes including cyber investigation and digital forensics. However, the use of such models for cyber investigation and digital forensics should…
Value trade-offs are an integral part of human decision-making and language use, however, current tools for interpreting such dynamic and multi-faceted notions of values in language models are limited. In cognitive science, so-called…
Large language models have recently shown promising progress in mathematical reasoning when fine-tuned with human-generated sequences walking through a sequence of solution steps. However, the solution sequences are not formally structured…