Related papers: Probing Minimalist Phase Structure in LLMs: What U…

We propose a geometric taxonomy of large language model hallucinations based on observable signatures in token embedding cluster structure. By analyzing the static embedding spaces of 11 transformer models spanning encoder (BERT, RoBERTa,…

Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, yet report AUROC exceeding 0.96 on clean benchmarks while collapsing under distributional shift. This paper systematically pressure-tests…

Large language models (LLMs) achieve impressive results on many benchmarks, yet their capacity for planning and stateful reasoning remains unclear. We study these abilities directly, without code execution or other tools, using the…

Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on…

Despite impressive capabilities, LLMs' successes often rely on pattern-matching behaviors, yet these are also linked to OOD generalization failures in compositional tasks. However, behavioral studies commonly employ task setups that allow…

Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redundant, or poorly grounded clusters that are difficult to validate without labeled data. We…

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

Multi-step theorem prediction is a central challenge in automated reasoning. Existing neural-symbolic approaches rely heavily on supervised parametric models, which exhibit limited generalization to evolving theorem libraries. In this work,…

We introduce a novel analysis that leverages linguistic minimal pairs to probe the internal linguistic representations of Large Language Models (LLMs). By measuring the similarity between LLM activation differences across minimal pairs, we…

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those…

Exploration and goal-directed navigation in unknown layouts are central to inspection, logistics, and search-and-rescue. We ask whether large language models (LLMs) can function as \emph{text-only} controllers under partial observability --…

Large language models (LLMs) have demonstrated strong performance in a wide-range of language tasks without requiring task-specific fine-tuning. However, they remain prone to hallucinations and inconsistencies, and often struggle with…

Existing hallucination detection methods for large language models (LLMs) rely on external verification at inference time, requiring gold answers, retrieval systems, or auxiliary judge models. We ask whether this external supervision can…

Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard step limits (abrupt) or LLM-as-judge monitoring (10-15%…

LLMs are increasingly used to draft academic text and to support software engineering (SE) evidence synthesis, but they often hallucinate bibliographic references that look legitimate. We study how deployment-motivated prompting constraints…

We discover that large language models exhibit \emph{spectral phase transitions} in their hidden activation spaces when engaging in reasoning versus factual recall. Through systematic spectral analysis across \textbf{11 models} spanning…

Large language models (LLMs) have demonstrated strong performance on formal language tasks, yet whether this reflects genuine symbolic reasoning or pattern matching on familiar constructions remains unclear. We introduce a benchmark for…

Large language models (LLMs) increasingly exhibit human-like patterns of pragmatic and social reasoning. This paper addresses two related questions: do LLMs approximate human social meaning not only qualitatively but also quantitatively,…

In this paper, we address the representation of coordinate constructions in Enhanced Universal Dependencies (UD), where relevant dependency links are propagated from conjunction heads to other conjuncts. English treebanks for enhanced UD…

Understanding whether large language models (LLMs) capture structured meaning requires examining how they represent concept relationships. In this work, we study three models of increasing scale: Pythia-70M, GPT-2, and Llama 3.1 8B,…