PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization

• URL: http://arxiv.org/abs/2507.16679v1
• Date: Tue, 22 Jul 2025 15:14:56 GMT
• Title: PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
• Authors: Han Jiang, Dongyao Zhu, Zhihua Wei, Xiaoyuan Yi, Ziang Xiao, Xing Xie,
• Abstract summary: In-Context Learning has shown great potential for aligning Large Language Models (LLMs) with human values.<n>LLMs' comprehension of input prompts remains agnostic, limiting ICA's ability to address value tensions.<n>We propose PICACO, a novel pluralistic ICA method to address this problem.
• Score: 33.60097751620483
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In-Context Learning has shown great potential for aligning Large Language Models (LLMs) with human values, helping reduce harmful outputs and accommodate diverse preferences without costly post-training, known as In-Context Alignment (ICA). However, LLMs' comprehension of input prompts remains agnostic, limiting ICA's ability to address value tensions--human values are inherently pluralistic, often imposing conflicting demands, e.g., stimulation vs. tradition. Current ICA methods therefore face the Instruction Bottleneck challenge, where LLMs struggle to reconcile multiple intended values within a single prompt, leading to incomplete or biased alignment. To address this, we propose PICACO, a novel pluralistic ICA method. Without fine-tuning, PICACO optimizes a meta-instruction that navigates multiple values to better elicit LLMs' understanding of them and improve their alignment. This is achieved by maximizing the total correlation between specified values and LLM responses, theoretically reinforcing value correlation while reducing distractive noise, resulting in effective value instructions. Extensive experiments on five value sets show that PICACO works well with both black-box and open-source LLMs, outperforms several recent strong baselines, and achieves a better balance across up to 8 distinct values.

Related papers

• Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences? [5.542420010310746]
  A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences and its revealed preferences.<n>This work formally defines and proposes a method to measure this preference deviation.<n>Our study will be crucial for integrating LLMs into services, especially those that interact directly with humans.
  arXiv  Detail & Related papers  (2025-05-31T23:38:48Z)
• AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference [43.168803869385066]
  AdAEM is a novel, self-extensible assessment framework for revealing LLMs' inclinations.<n>It can automatically and adaptively generate and extend its test questions.<n>We generate 12,310 questions grounded in Schwartz Value Theory, conduct an analysis to manifest our method's validity and effectiveness, and benchmark the values of 16 LLMs.
  arXiv  Detail & Related papers  (2025-05-18T09:15:26Z)
• SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [74.40683913645731]
  Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications.<n>Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth.<n>Analysis of these prompt scores reveals VLM biases and AND''/OR' signal ambiguities, notably that maximum scores are surprisingly suboptimal compared to second-highest scores.
  arXiv  Detail & Related papers  (2025-02-24T07:15:05Z)
• Value Compass Benchmarks: A Platform for Fundamental and Validated Evaluation of LLMs Values [76.70893269183684]
  Large Language Models (LLMs) achieve remarkable breakthroughs.<n> aligning their values with humans has become imperative for their responsible development.<n>There still lack evaluations of LLMs values that fulfill three desirable goals.
  arXiv  Detail & Related papers  (2025-01-13T05:53:56Z)
• AIME: AI System Optimization via Multiple LLM Evaluators [79.03422337674664]
  AIME is an evaluation protocol that utilizes multiple LLMs that each independently generate an evaluation on separate criteria and then combine them via concatenation. We show AIME outperforming baseline methods in code generation tasks, with up to $62%$ higher error detection rate and up to $16%$ higher success rate than a single LLM evaluation protocol on LeetCodeHard and HumanEval datasets.
  arXiv  Detail & Related papers  (2024-10-04T04:03:24Z)
• CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses [34.77031649891843]
  We introduce CLAVE, a novel framework which integrates two complementary Large Language Models (LLMs) This dual-model approach enables calibration with any value systems using 100 human-labeled samples per value type. We present ValEval, a comprehensive dataset comprising 13k+ (text,value,label) 12+s across diverse domains, covering three major value systems.
  arXiv  Detail & Related papers  (2024-07-15T13:51:37Z)
• DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback [61.28463542324576]
  We present DRESS, a large vision language model (LVLM) that innovatively exploits Natural Language feedback (NLF) from Large Language Models. We propose a novel categorization of the NLF into two key types: critique and refinement. Our experimental results demonstrate that DRESS can generate more helpful (9.76%), honest (11.52%), and harmless (21.03%) responses.
  arXiv  Detail & Related papers  (2023-11-16T18:37:29Z)
• Flames: Benchmarking Value Alignment of LLMs in Chinese [86.73527292670308]
  This paper proposes a value alignment benchmark named Flames. It encompasses both common harmlessness principles and a unique morality dimension that integrates specific Chinese values. Our findings indicate that all the evaluated LLMs demonstrate relatively poor performance on Flames.
  arXiv  Detail & Related papers  (2023-11-12T17:18:21Z)
• Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics [32.123919380959485]
  Multi-modal large language models (MLLMs) are trained based on large language models (LLM) While they excel in multi-modal tasks, the pure NLP abilities of MLLMs are often underestimated and left untested. We show that visual instruction tuning, a prevailing strategy for transitioning LLMs into MLLMs, unexpectedly and interestingly helps models attain both improved truthfulness and ethical alignment.
  arXiv  Detail & Related papers  (2023-09-13T17:57:21Z)
• Heterogeneous Value Alignment Evaluation for Large Language Models [91.96728871418]
  Large Language Models (LLMs) have made it crucial to align their values with those of humans. We propose a Heterogeneous Value Alignment Evaluation (HVAE) system to assess the success of aligning LLMs with heterogeneous values.
  arXiv  Detail & Related papers  (2023-05-26T02:34:20Z)

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.