English
Related papers

Related papers: Split Personality Training: Revealing Latent Knowl…

200 papers

We propose SPARTA ALIGNMENT, an algorithm to collectively align multiple LLMs through competition and combat. To complement a single model's lack of diversity in generation and biases in evaluation, multiple LLMs form a "sparta tribe" to…

Computation and Language · Computer Science 2025-11-04 Yuru Jiang , Wenxuan Ding , Shangbin Feng , Greg Durrett , Yulia Tsvetkov

Large language models (LLMs) are increasingly used both to make decisions in domains such as health, education and law, and to simulate human behavior. Yet how closely LLMs mirror actual human decision-making remains poorly understood. This…

Artificial Intelligence · Computer Science 2025-11-26 Andrea Cera Palatsi , Samuel Martin-Gutierrez , Ana S. Cardenal , Max Pellert

The performance of Large Language Models (LLMs) relies heavily on the quality of prompts, which are often manually engineered and task-specific, making them costly and non-scalable. We propose a novel approach, Supervisory Prompt Training…

Computation and Language · Computer Science 2024-03-28 Jean Ghislain Billa , Min Oh , Liang Du

We evaluated 4 systems (ELIZA, GPT-4o, LLaMa-3.1-405B, and GPT-4.5) in two randomised, controlled, and pre-registered Turing tests on independent populations. Participants had 5 minute conversations simultaneously with another human…

Computation and Language · Computer Science 2025-04-01 Cameron R. Jones , Benjamin K. Bergen

Although Large Language Models (LLMs) have become capable reasoners, the problem of faithfulness persists: their reasoning can contain errors and omissions that are difficult to detect and that may obscure biases in model outputs. To…

Computation and Language · Computer Science 2025-09-30 Jixuan Leng , Cassandra A. Cohen , Zhixian Zhang , Chenyan Xiong , William W. Cohen

Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT)…

Artificial Intelligence · Computer Science 2025-06-04 Chen Qian , Dongrui Liu , Jie Zhang , Yong Liu , Jing Shao

Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big…

Computation and Language · Computer Science 2025-09-08 Gunmay Handa , Zekun Wu , Adriano Koshiyama , Philip Treleaven

Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing political sides asymmetrically. We refer to this phenomenon as covert political…

Computation and Language · Computer Science 2026-05-29 Long Phan , Devin Kim , Alexander Pan , Alice Blair , Adam Khoja , Dan Hendrycks

Despite investments in improving model safety, studies show that misaligned capabilities remain latent in safety-tuned models. In this work, we shed light on the mechanics of this phenomenon. First, we show that even when model generations…

Computation and Language · Computer Science 2024-08-14 Asma Ghandeharioun , Ann Yuan , Marius Guerard , Emily Reif , Michael A. Lepori , Lucas Dixon

Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human…

Computation and Language · Computer Science 2023-10-10 Yi Dong , Zhilin Wang , Makesh Narsimhan Sreedhar , Xianchao Wu , Oleksii Kuchaiev

Fine-tuning large language models (LLMs) often causes overfitting to specific prompt wording, where minor phrasing variations drastically reduce performance. To address this, we propose Prompt-Agnostic Fine-Tuning (PAFT), a method that…

Computation and Language · Computer Science 2025-10-20 Chenxing Wei , Yao Shu , Mingwen Ou , Ying Tiffany He , Fei Richard Yu

Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like…

Machine Learning · Computer Science 2026-01-21 Xingtai Lv , Yuxin Zuo , Youbang Sun , Hongyi Liu , Yuntian Wei , Zhekai Chen , Xuekai Zhu , Kaiyan Zhang , Bingning Wang , Ning Ding , Bowen Zhou

While LLM-based TTS models exhibit zero-shot emotion and speaker cloning, their cloning fidelity and pronunciation clarity degrade on unseen domains. Fine-tuning is essential for adaptation, yet uniform approaches overlook specific…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-09 Tianrui Wang , Meng Ge , Cheng Gong , Chunyu Qiang , Haoyu Wang , Zikang Huang , Yu Jiang , Ye Ni , Yuheng Lu , Xiaobao Wang , Engsiong Chng , Xie Chen , Longbiao Wang , Jianwu Dang

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…

Machine Learning · Computer Science 2026-03-24 Andrey Goncharov , Daniil Vyazhev , Petr Sychev , Edvard Khalafyan , Alexey Zaytsev

Pre-trained foundation models can be adapted for specific tasks using Low-Rank Adaptation (LoRA). However, the fairness properties of these adapted classifiers remain underexplored. Existing fairness-aware fine-tuning methods rely on direct…

Machine Learning · Computer Science 2025-03-10 Parameswaran Kamalaruban , Mark Anderson , Stuart Burrell , Maeve Madigan , Piotr Skalski , David Sutton

The Split and Rephrase (SPRP) task, which consists in splitting complex sentences into a sequence of shorter grammatical sentences, while preserving the original meaning, can facilitate the processing of complex texts for humans and…

Computation and Language · Computer Science 2024-10-11 David Ponce , Thierry Etchegoyhen , Jesús Calleja Pérez , Harritxu Gete

Instruction tuning -- supervised fine-tuning using instruction-response pairs -- is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring…

Computation and Language · Computer Science 2025-09-16 Seokhyun An , Minji Kim , Hyounghun Kim

Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. In SL training with multiple clients, the local model weights are shared among the clients for local…

Cryptography and Security · Computer Science 2024-07-23 Ngoc Duy Pham , Tran Khoa Phan , Alsharif Abuadbba , Yansong Gao , Doan Nguyen , Naveen Chilamkurti

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks. Yet ensuring that the reasoning trace both contributes to and faithfully reflects the processes underlying the model's final answer,…

Computation and Language · Computer Science 2026-04-20 Max Henning Höth , Kristian Kersting , Björn Deiseroth , Letitia Parcalabescu

The pretraining and fine-tuning approach has become the leading technique for various NLP applications. However, recent studies reveal that fine-tuning data, due to their sensitive nature, domain-specific characteristics, and…

Computation and Language · Computer Science 2024-11-13 Qian Sun , Hanpeng Wu , Xi Sheryl Zhang
‹ Prev 1 3 4 5 6 7 10 Next ›