相关论文: When and How Long? The Readout-Mediator Angle in T…

Medical reasoning models remain constrained by parametric knowledge and are thus susceptible to forgetting and hallucinations. DeepResearch (DR) models ground outputs in verifiable evidence from tools and perform strongly in general…

In psycholinguistic modeling, surprisal from larger pre-trained language models has been shown to be a poorer predictor of naturalistic human reading times. However, it has been speculated that this may be due to data leakage that caused…

When a language model agrees with a user's false belief, is it failing to detect the error, or noticing and agreeing anyway? We show the latter. Across twelve open-weight models from five labs, spanning small to frontier scale, the same…

This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses functionally ordered, step-specific subspaces that become…

Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the…

This project reproduces and extends the recently proposed ``Recursive Language Models'' (RLMs) framework by Zhang et al. (2026). This framework enables Large Language Models (LLMs) to process near-infinite contexts by offloading the prompt…

As reasoning modules, such as the chain-of-thought mechanism, are applied to large language models, they achieve strong performance on various tasks such as answering common-sense questions and solving math problems. The main challenge now…

Holistic evaluation scores capture overall output quality but do not distinguish whether a model reproduced the structural form of a user's request from whether it preserved the user's specific intent. We propose a dimension-level intent…

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…

While Large Language Models (LLMs) excel at temporal reasoning tasks like event ordering and duration estimation, their ability to perceive the actual passage of time remains unexplored. We investigate whether LLMs perceive the passage of…

A new generation of language models reasons entirely in continuous hidden states, producing no tokens and leaving no audit trail. We show that this silence creates a fundamentally new attack surface. ThoughtSteer perturbs a single embedding…

Many non-equilibrium, active processes are observed at a coarse-grained level, where different microscopic configurations are projected onto the same observable state. Such "lumped" observables display memory, and in many cases the…

Recent advances in Natural Language Processing (NLP) have led to the development of highly sophisticated language models for text generation. In parallel, neuroscience has increasingly employed these models to explore cognitive processes…

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning…

We find that correct-to-incorrect sycophancy signals are most linearly separable within multi-head attention activations. Motivated by the linear representation hypothesis, we train linear probes across the residual stream, multilayer…

The Rotary Position Embedding (RoPE) is widely used in the attention heads of many large language models (LLM). It rotates dimensions in the query and the key vectors by different angles according to their positions in the input sequence.…

Latent reasoning models (LRMs) have attracted significant research interest due to their low inference cost (relative to explicit reasoning models) and theoretical ability to explore multiple reasoning paths in parallel. However, these…

LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify…

Large language models (LLMs) exhibit strong symbolic and compositional reasoning, yet they struggle with time series question answering as the data is typically transformed into an LLM-compatible modality, e.g., serialized text, plotted…

Due to simplicity and strong stability guarantees, predictor feedback methods have stood as a popular approach for time delay systems since the 1950s. For time-varying delays, however, implementation requires computing a prediction horizon…