中文
相关论文

相关论文: Steering Conversational Large Language Models for …

200 篇论文

With the incredible advancements in Large Language Models (LLMs), many people have started using them to satisfy their information needs. However, utilizing LLMs might be problematic for political issues where disagreement is common and…

计算机与社会 · 计算机科学 2026-01-27 Salah Feras Alali , Mohammad Nashat Maasfeh , Mucahid Kutlu , Saban Kardas

Large Language Models (LLMs) demonstrate remarkable capabilities in text generation, yet their emotional consistency and semantic coherence in social media contexts remain insufficiently understood. This study investigates how LLMs handle…

计算与语言 · 计算机科学 2025-11-05 Wentao Xu , Wenlu Fan , Yuqi Zhu , Bin Wang

Large language models (LLMs) are employed to simulate human-like responses in social surveys, yet it remains unclear if they develop biases like social desirability response (SDR) bias. To investigate this, GPT-4 was assigned personas from…

人工智能 · 计算机科学 2024-10-22 Sanguk Lee , Kai-Qi Yang , Tai-Quan Peng , Ruth Heo , Hui Liu

The advent of large language models (LLMs) has gained tremendous attention over the past year. Previous studies have shown the astonishing performance of LLMs not only in other tasks but also in emotion recognition in terms of accuracy,…

计算与语言 · 计算机科学 2023-10-24 Liyizhe Peng , Zixing Zhang , Tao Pang , Jing Han , Huan Zhao , Hao Chen , Björn W. Schuller

Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence, limiting their reliability in critical applications. We propose SteerConf, a novel framework that systematically steers…

计算与语言 · 计算机科学 2025-05-27 Ziang Zhou , Tianyuan Jin , Jieming Shi , Qing Li

We investigate the use of Large Language Models (LLMs) for zero-shot prediction of Ryff Psychological Well-Being (PWB) scores from spontaneous speech. Using a few minutes of voice recordings from 111 participants in the PsyVoiD database, we…

计算与语言 · 计算机科学 2026-05-13 Erfan Loweimi , Sofia de la Fuente Garcia , Saturnino Luz

Evaluating true metacognition in Large Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to measure and enhance LLM metacognition while controlling for these biases. A measurement method using…

神经与进化计算 · 计算机科学 2026-05-26 Sangjun Park , Elliot Meyerson , Xin Qiu , Risto Miikkulainen

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

计算与语言 · 计算机科学 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based…

计算与语言 · 计算机科学 2025-08-08 Wenqian Cui , Dianzhi Yu , Xiaoqi Jiao , Ziqiao Meng , Guangyan Zhang , Qichao Wang , Yiwen Guo , Irwin King

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

机器学习 · 计算机科学 2025-03-04 Reza Bayat , Ali Rahimi-Kalahroudi , Mohammad Pezeshki , Sarath Chandar , Pascal Vincent

Large language models (LLMs) achieve state-of-the-art performance on multiple language tasks, yet their safety guardrails can be circumvented, leading to harmful generations. In light of this, recent research on safety mechanisms has…

计算与语言 · 计算机科学 2025-02-25 Zhenhong Zhou , Haiyang Yu , Xinghua Zhang , Rongwu Xu , Fei Huang , Kun Wang , Yang Liu , Junfeng Fang , Yongbin Li

Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities,…

计算与语言 · 计算机科学 2025-02-18 Shu Yang , Shenzhe Zhu , Liang Liu , Lijie Hu , Mengdi Li , Di Wang

The growing need to integrate information from a large number of diverse sources poses significant scalability challenges for data integration systems. These systems often rely on manually written schema mappings, which are complex,…

数据库 · 计算机科学 2025-06-02 Christopher Buss , Mahdis Safari , Arash Termehchy , Stefan Lee , David Maier

In schema-guided dialogue state tracking models estimate the current state of a conversation using natural language descriptions of the service schema for generalization to unseen services. Prior generative approaches which decode slot…

计算与语言 · 计算机科学 2023-06-16 Björn Bebensee , Haejun Lee

Large language models (LLMs) have made significant strides, extending their applications to dialogue systems, automated content creation, and domain-specific advisory tasks. However, as their use grows, concerns have emerged regarding their…

人工智能 · 计算机科学 2025-07-01 Bing Song , Jianing Liu , Sisi Jian , Chenyang Wu , Vinayak Dixit

Large language models (LLMs) have advanced the state of the art in natural language processing. However, their predominant design for English or a limited set of languages creates a substantial gap in their effectiveness for low-resource…

计算与语言 · 计算机科学 2024-04-04 Peiqin Lin , Shaoxiong Ji , Jörg Tiedemann , André F. T. Martins , Hinrich Schütze

In this work, we investigate how small language models (SLMs) can be scaled to support multimodal search and recommendation use cases while remaining efficient enough for real-time, resource-constrained deployments. We present a framework…

计算与语言 · 计算机科学 2025-12-04 Yu-Chen Lin , Sanat Sharma , Hari Manikandan , Jayant Kumar , Tracy Holloway King , Jing Zheng

Large-language models (LLMs) hold significant promise in improving human-robot interaction, offering advanced conversational skills and versatility in managing diverse, open-ended user requests in various tasks and domains. Despite the…

机器人学 · 计算机科学 2024-01-09 Callie Y. Kim , Christine P. Lee , Bilge Mutlu

Precisely understanding users' contextual search intent has been an important challenge for conversational search. As conversational search sessions are much more diverse and long-tailed, existing methods trained on limited data still show…

信息检索 · 计算机科学 2023-10-23 Kelong Mao , Zhicheng Dou , Fengran Mo , Jiewen Hou , Haonan Chen , Hongjin Qian

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

机器学习 · 计算机科学 2026-02-04 Magamed Taimeskhanov , Samuel Vaiter , Damien Garreau