As interest grows in applying natural language processing (NLP) techniques to mental health, an expanding body of work explores the automatic detection and classification of cognitive distortions (CDs). CDs are habitual patterns of negatively biased or flawed thinking that distort how people perceive events, judge themselves, and react to the world. Identifying and addressing them is a central goal of therapy. Despite this momentum, the field remains fragmented, with inconsistencies in CD taxonomies, task formulations, and evaluation practices limiting comparability across studies. This survey presents the first comprehensive review of 38 studies spanning two decades, mapping how CDs have been implemented in computational research and evaluating the methods applied. We provide a consolidated CD taxonomy reference, summarise common task setups, and highlight persistent challenges to support more coherent and reproducible research. Alongside our review, we introduce practical resources, including curated evaluation metrics from surveyed papers, a standardised datasheet template, and an ethics flowchart, available online.

Large Language Models (LLMs) have shown remarkable capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG), which enhances knowledge grounding, and Reinforcement Learning from Verifiable Rewards (RLVR), which optimizes complex reasoning abilities. However, these two capabilities are often developed in isolation, and existing efforts to unify them remain narrow in scope -- typically limited to open-domain QA with fixed retrieval settings and task-specific constraints. This lack of integration constrains generalization and limits the applicability of RAG-RL methods to broader domains. To bridge this gap, we propose UR2 (Unified RAG and Reasoning), a general framework that unifies retrieval and reasoning through reinforcement learning. UR2 introduces two key contributions: a difficulty-aware curriculum training that selectively invokes retrieval only for challenging problems, and a hybrid knowledge access strategy combining domain-specific offline corpora with LLM-generated summaries. These components are designed to enable dynamic coordination between retrieval and reasoning, improving adaptability across a diverse range of tasks. Experiments across open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks demonstrate that UR$^2$ (built on Qwen-2.5-3/7B and LLaMA-3.1-8B) significantly outperforms existing RAG and RL methods, achieving comparable performance to GPT-4o-mini and GPT-4.1-mini on several benchmarks. We have released all code, models, and data at https://github.com/Tsinghua-dhy/UR2.

Generative agents powered by Large Language Models demonstrate human-like characteristics through sophisticated natural language interactions. Their ability to assume roles and personalities based on predefined character biographies has positioned them as cost-effective substitutes for human participants in social science research. This paper explores the validity of such persona-based agents in representing human populations; we recreate the HEXACO personality inventory experiment by surveying 310 GPT-4 powered agents, conducting factor analysis on their responses, and comparing these results to the original findings presented by Ashton, Lee, & Goldberg in 2004. Our results found 1) a coherent and reliable personality structure was recoverable from the agents' responses demonstrating partial alignment to the HEXACO framework. 2) the derived personality dimensions were consistent and reliable within GPT-4, when coupled with a sufficiently curated population, and 3) cross-model analysis revealed variability in personality profiling, suggesting model-specific biases and limitations. We discuss the practical considerations and challenges encountered during the experiment. This study contributes to the ongoing discourse on the potential benefits and limitations of using generative agents in social science research and provides useful guidance on designing consistent and representative agent personas to maximise coverage and representation of human personality traits.

Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs' significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models. While Speculative Decoding (SD) has shown efficacy in accelerating Large Language Models (LLMs) by incorporating efficient drafting and parallel verification, allowing multiple tokens to be generated in one forward pass, its application to VLA models remains unexplored. This work introduces Spec-VLA, an SD framework designed to accelerate VLA models. Due to the difficulty of the action prediction task and the greedy decoding mechanism of the VLA models, the direct application of the advanced SD framework to the VLA prediction task yields a minor speed improvement. To boost the generation speed, we propose an effective mechanism to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model. Empirical results across diverse test scenarios affirm the effectiveness of the Spec-VLA framework, and further analysis substantiates the impact of our proposed strategies, which enhance the acceptance length by 44%, achieving 1.42 times speedup compared with the OpenVLA baseline, without compromising the success rate. The success of the Spec-VLA framework highlights the potential for broader application of speculative execution in VLA prediction scenarios.

Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas. In this study, we examine how assigning a persona influences a model's reasoning on an objective task. Using activation patching, we take a first step toward understanding how key components of the model encode persona-specific information. Our findings reveal that the early Multi-Layer Perceptron (MLP) layers attend not only to the syntactic structure of the input but also process its semantic content. These layers transform persona tokens into richer representations, which are then used by the middle Multi-Head Attention (MHA) layers to shape the model's output. Additionally, we identify specific attention heads that disproportionately attend to racial and color-based identities.

Large language models (LLMs) are increasingly integrated into users' daily lives, leading to a growing demand for personalized outputs. Previous work focuses on leveraging a user's own history, overlooking inter-user differences that are crucial for effective personalization. While recent work has attempted to model such differences, the reliance on language-based prompts often hampers the effective extraction of meaningful distinctions. To address these issues, we propose Difference-aware Embedding-based Personalization (DEP), a framework that models inter-user differences in the latent space instead of relying on language prompts. DEP constructs soft prompts by contrasting a user's embedding with those of peers who engaged with similar content, highlighting relative behavioral signals. A sparse autoencoder then filters and compresses both user-specific and difference-aware embeddings, preserving only task-relevant features before injecting them into a frozen LLM. Experiments on personalized review generation show that DEP consistently outperforms baseline methods across multiple metrics. Our code is available at https://github.com/SnowCharmQ/DEP.

The quality of a conversation goes beyond the individual quality of each reply, and instead emerges from how these combine into interactional dynamics that give the conversation its distinctive overall "shape". However, there is no robust automated method for comparing conversations in terms of their overall dynamics. Such methods could enhance the analysis of conversational data and help evaluate conversational agents more holistically. In this work, we introduce a similarity measure for comparing conversations with respect to their dynamics. We design a validation procedure for testing the robustness of the metric in capturing differences in conversation dynamics and for assessing its sensitivity to the topic of the conversations. To illustrate the measure's utility, we use it to analyze conversational dynamics in a large online community, bringing new insights into the role of situational power in conversations.

We run a controlled compositional generalization experiment in the ARC-AGI domain: an open-world problem domain in which the ability to generalize out-of-distribution is, by design, an essential characteristic for success. We compare neural program synthesis and test-time fine-tuning approaches on this experiment. We find that execution-guided neural program synthesis outperforms all reference algorithms in its ability to compose novel solutions. Our empirical findings also suggest that the success of TTFT on ARC-AGI lies mainly in eliciting in-distribution knowledge that the LLM otherwise fails to rely on directly.

As AI systems take on collaborative roles, they must reason about shared goals and beliefs-not just generate fluent language. The Rational Speech Act (RSA) framework offers a principled approach to pragmatic reasoning, but existing extensions face challenges in scaling to multi-turn, collaborative scenarios. In this paper, we introduce Collaborative Rational Speech Act (CRSA), an information-theoretic (IT) extension of RSA that models multi-turn dialog by optimizing a gain function adapted from rate-distortion theory. This gain is an extension of the gain model that is maximized in the original RSA model but takes into account the scenario in which both agents in a conversation have private information and produce utterances conditioned on the dialog. We demonstrate the effectiveness of CRSA on referential games and template-based doctor-patient dialogs in the medical domain. Empirical results show that CRSA yields more consistent, interpretable, and collaborative behavior than existing baselines-paving the way for more pragmatic and socially aware language agents.

The rapid advancement of large language models (LLMs) has heightened concerns about benchmark data contamination (BDC), where models inadvertently memorize evaluation data during the training process, inflating performance metrics, and undermining genuine generalization assessment. This paper introduces the Data Contamination Risk (DCR) framework, a lightweight, interpretable pipeline designed to detect and quantify BDC risk across four granular levels: semantic, informational, data, and label. By synthesizing contamination scores via a fuzzy inference system, DCR produces a unified DCR Factor that adjusts raw accuracy to reflect contamination-aware performance. Validated on 9 LLMs (0.5B-72B) across sentiment analysis, fake news detection, and arithmetic reasoning tasks, the DCR framework reliably diagnoses contamination severity and with accuracy adjusted using the DCR Factor to within 4% average error across the three benchmarks compared to the uncontaminated baseline. Emphasizing computational efficiency and transparency, DCR provides a practical tool for integrating contamination assessment into routine evaluations, fostering fairer comparisons and enhancing the credibility of LLM benchmarking practices.