UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation

• URL: http://arxiv.org/abs/2310.16582v3
• Date: Tue, 09 Sep 2025 14:42:44 GMT
• Title: UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation
• Authors: Tianlong Li, Wenhao Liu, Muling Wu, Shihan Dou, Zhenghua Wang, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang,
• Abstract summary: Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs)<n>We propose UPLex, a method that uses an Unsupervisedly-Built personalized lexicon (UPL) during the decoding phase to manipulate LLM's personality traits.<n>UPLex can be constructed from a newly built situational judgment test dataset in an unsupervised fashion, and used to modulate the personality expression of LLMs.
• Score: 52.043831554626685
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs) holds significant potential in enhancing their user experiences. Previous approaches either relied on fine-tuning LLMs on specific corpora or required manually crafted prompts to evoke specific personalities from LLMs. However, the former is inefficient and costly, while the latter cannot precisely manipulate personality traits at a fine-grained level. To address these challenges, we propose UPLex, a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM's personality traits. UPL can be constructed from a newly built situational judgment test dataset in an unsupervised fashion, and used to modulate the personality expression of LLMs by dynamically altering their predicted probability of upcoming words in a pluggable fashion. Extensive experimentation demonstrates the remarkable effectiveness and pluggability of our method for fine-grained manipulation of LLMs' personalities.

Related papers

• Self-Correction Makes LLMs Better Parsers [19.20952673157709]
  Large language models (LLMs) have achieved remarkable success across various natural language processing (NLP) tasks. Recent studies suggest that they still face challenges in performing fundamental NLP tasks essential for deep language understanding. We propose a self-correction method that leverages grammar rules from existing treebanks to guide LLMs in correcting previous errors.
  arXiv  Detail & Related papers  (2025-04-19T03:50:59Z)
• Probing then Editing Response Personality of Large Language Models [40.99117085818623]
  Large Language Models (LLMs) have demonstrated promising capabilities to generate responses that exhibit consistent personality traits. We introduce a layer-wise probing framework to investigate the layer-wise capability of LLMs in encoding personality for responding. We propose a layer-wise editing method to edit the personality expressed by LLMs during inference.
  arXiv  Detail & Related papers  (2025-04-14T13:46:35Z)
• Personality Editing for Language Models through Adjusting Self-Referential Queries [17.051166122108857]
  We present PALETTE (Personality Adjustment by LLM SElf-TargeTed quEries), a novel method for personality editing in Large Language Models (LLMs)<n>Our approach introduces adjustment queries, where self-referential statements grounded in psychological constructs are treated analogously to factual knowledge, enabling direct editing of personality-related responses.<n>Unlike fine-tuning, PALETTE requires only 12 editing samples to achieve substantial improvements in personality alignment across personality dimensions.
  arXiv  Detail & Related papers  (2025-02-17T13:28:14Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression. LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model. Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• LMLPA: Language Model Linguistic Personality Assessment [11.599282127259736]
  Large Language Models (LLMs) are increasingly used in everyday life and research. measuring the personality of a given LLM is currently a challenge. This paper introduces the Language Model Linguistic Personality Assessment (LMLPA), a system designed to evaluate the linguistic personalities of LLMs.
  arXiv  Detail & Related papers  (2024-10-23T07:48:51Z)
• zsLLMCode: An Effective Approach for Functional Code Embedding via LLM with Zero-Shot Learning [6.976968804436321]
  Large language models (LLMs) have the capability of zero-shot learning, which does not require training or fine-tuning. We propose zsLLMCode, a novel approach that generates functional code embeddings using LLMs.
  arXiv  Detail & Related papers  (2024-09-23T01:03:15Z)
• LLMvsSmall Model? Large Language Model Based Text Augmentation Enhanced Personality Detection Model [58.887561071010985]
  Personality detection aims to detect one's personality traits underlying in social media posts. Most existing methods learn post features directly by fine-tuning the pre-trained language models. We propose a large language model (LLM) based text augmentation enhanced personality detection model.
  arXiv  Detail & Related papers  (2024-03-12T12:10:18Z)
• Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension [63.330262740414646]
  We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs) We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
  arXiv  Detail & Related papers  (2024-02-28T04:56:21Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• Psychometric Predictive Power of Large Language Models [32.31556074470733]
  We find that instruction tuning does not always make large language models human-like from a cognitive modeling perspective. Next-word probabilities estimated by instruction-tuned LLMs are often worse at simulating human reading behavior than those estimated by base LLMs.
  arXiv  Detail & Related papers  (2023-11-13T17:19:14Z)
• Let Models Speak Ciphers: Multiagent Debate through Embeddings [84.20336971784495]
  We introduce CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. By deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs.
  arXiv  Detail & Related papers  (2023-10-10T03:06:38Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• Personality Traits in Large Language Models [44.908741466152215]
  Personality is a key factor determining the effectiveness of communication. We present a comprehensive method for administering and validating personality tests on widely-used large language models. We discuss application and ethical implications of the measurement and shaping method, in particular regarding responsible AI.
  arXiv  Detail & Related papers  (2023-07-01T00:58:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.