Related papers: Abstract Activation Spaces for Content-Invariant R…

Large Language Models (LLMs) have transformed natural language processing and hold growing promise for advancing science, healthcare, and decision-making. Yet their training paradigms remain dominated by affirmation-based inference, akin to…

Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in…

Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intelligence. While prior surveys focus on efficiency by examining how to shorten reasoning chains or reduce computation, this view…

Despite the ubiquity of large language models (LLMs) in AI research, the question of embodiment in LLMs remains underexplored, distinguishing them from embodied systems in robotics where sensory perception directly informs physical action.…

Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood. Existing interpretability research has primarily…

The need for modelling causal knowledge at different levels of granularity arises in several settings. Causal Abstraction provides a framework for formalizing this problem by relating two Structural Causal Models at different levels of…

Language models (LMs) trained on large quantities of text have been claimed to acquire abstract linguistic representations. Our work tests the robustness of these abstractions by focusing on the ability of LMs to learn interactions between…

Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes…

While Large Language Models (LLMs) have showcased remarkable proficiency in reasoning, there is still a concern about hallucinations and unreliable reasoning issues due to semantic associations and superficial logical chains. To evaluate…

Large language models (LLMs) are increasingly utilized in various complex reasoning tasks due to their excellent instruction following capability. However, the model's performance is highly dependent on the open-ended characteristics of the…

Sparse activation, which selectively activates only an input-dependent set of neurons in inference, is a useful technique to reduce the computing cost of Large Language Models (LLMs) without retraining or adaptation efforts. However,…

Abstraction--the ability to recognize and distill essential computational patterns from complex problem statements--is a foundational skill in computer science, critical both for human problem-solvers and coding-oriented large language…

Large language models (LLMs) are increasingly used to make sense of ambiguous, open-textured, value-laden terms. Platforms routinely rely on LLMs for content moderation, asking them to label text based on disputed concepts like "hate…

Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, they often preclude direct interpretation. While downstream…

Large language models (LLMs) exhibit impressive capabilities but struggle with reasoning errors due to hallucinations and flawed logic. To investigate their internal representations of reasoning, we introduce ArrangementPuzzle, a novel…

Communication between multiple language model (LM) agents has been shown to scale up the reasoning ability of LMs. While natural language has been the dominant medium for inter-LM communication, it is not obvious this should be the…

What underlies intuitive human thinking? One approach to this question is to compare the cognitive dynamics of humans and large language models (LLMs). However, such a comparison requires a method to quantitatively analyze AI cognitive…

This work investigates whether knowledge-driven large language model (LLM)-based storytelling can support purposeful narrative interaction with a digital companion for older adults. To address known limitations of LLMs, including…

Images usually convey richer detail than text, but often include redundant information, which potentially downgrades multimodal reasoning performance. When faced with lengthy or complex messages, humans tend to employ abstract thinking to…

Inductive reasoning is a core problem-solving capacity: humans can identify underlying principles from a few examples, which robustly generalize to novel scenarios. Recent work evaluates large language models (LLMs) on inductive reasoning…