相关论文: Quantitative Introspection in Language Models: Tra…

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…

As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we…

The versatility of Large Language Models (LLMs) on natural language understanding tasks has made them popular for research in social sciences. To properly understand the properties and innate personas of LLMs, researchers have performed…

Background: Motivational interviewing (MI) is an effective counseling approach for promoting health behavior change, but its impact is constrained by the need for highly trained human counselors. Objective: This study aimed to explore a…

Large Language Models (LLMs) excel in handling general knowledge tasks, yet they struggle with user-specific personalization, such as understanding individual emotions, writing styles, and preferences. Personalized Large Language Models…

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…

Privacy preservation is a crucial component of any real-world application. But, in applications relying on machine learning backends, privacy is challenging because models often capture more than what the model was initially trained for,…

Self-correction has achieved impressive results in enhancing the style and security of the generated output from large language models (LLMs). However, recent studies suggest that self-correction might be limited or even counterproductive…

Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved information, with no clear or…

The exponential growth of social media and generative AI has transformed information dissemination, fostering connectivity but also accelerating the spread of misinformation. Understanding information propagation dynamics and developing…

Existing large language models (LLMs) evaluations use fixed-difficulty benchmarks that cannot adapt as models improve, and rarely isolate specific cognitive processes. We introduce Working Memory Fidelity-Active Manipulation (WMF-AM), a…

Large language models, LLMs, are increasingly deployed in multiturn settings where earlier responses shape later ones, making reliability dependent on whether a conversation remains consistent over time. When this consistency degrades…

Large language models (LLMs) possess strong persuasive capabilities that outperform humans in head-to-head comparisons. Users report consulting LLMs to inform major life decisions in relationships, medical settings, and when seeking…

Large Language Models (LLMs) have demonstrated remarkable self-improvement capabilities, whereby models iteratively revise their outputs through self-generated feedback. While this reflective mechanism has shown promise in enhancing task…

Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped Transformers (LTs)--architectures that increase computational…

The inability of Large Language Models (LLMs) to modulate their personality expression in response to evolving dialogue dynamics hinders their performance in complex, interactive contexts. We propose a model-agnostic framework for dynamic…

Student simulation with Large language models (LLMs) offers a scalable alternative for educational research and teacher training. Yet, its validity depends on whether models maintain stable personas across extended interactions. We test…

Human-like personality traits have recently been discovered in large language models, raising the hypothesis that their (known and as yet undiscovered) biases conform with human latent psychological constructs. While large conversational…

Large language models (LLMs) can carry out human-like dialogue, but unlike humans, they are stateless due to the superposition property. However, during multi-turn, multi-agent interactions, LLMs begin to exhibit consistent, character-like…

Recent reasoning language models, particularly those that employ long latent chains of thought, achieve strong performance on complex agentic tasks. However, as these models operate over increasingly long time horizons, their internal…