SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.07900 · 2024

High-Dimension Human Value Representation in Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
hltchkust/univar canonical 5 of 8
FunctionStatusWhere it lives
cohere_api Ran hltchkust/univar/value_eliciting_qa_generation/gen_answer_llm_api.py
code served (permissive licence) · get_code("eb2ad3cbb871e2dc")
encode_qas Ran hltchkust/univar/univar_evaluation/utils.py
code served (permissive licence) · get_code("f470fcd7a858340e")
encode_value_dataset Ran hltchkust/univar/univar_evaluation/utils.py
code served (permissive licence) · get_code("0c8b356a9662e596")
openai_api Ran hltchkust/univar/value_eliciting_qa_generation/gen_answer_llm_api.py
code served (permissive licence) · get_code("fe45f2f57cad641a")
seallm_chat_convo_format Ran hltchkust/univar/value_eliciting_qa_generation/gen_answer_llm.py
code served (permissive licence) · get_code("c5ae1d59e9767e2a")
claude_api Not yet run hltchkust/univar/value_eliciting_qa_generation/gen_answer_llm_api.py
code served (permissive licence) · get_code("590375b28ecf1908")
expand_sentence_transformer_encoder Not yet run hltchkust/univar/univar_evaluation/utils.py
code served (permissive licence) · get_code("ee131ced5327bd24")
get_situation_qa Not yet run hltchkust/univar/value_eliciting_qa_generation/generate_prompt.py
code served (permissive licence) · get_code("b332df303673d0d9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The widespread application of LLMs across various tasks and fields has necessitated the alignment of these models with human values and preferences. Given various approaches of human value alignment, there is an urgent need to understand the scope and nature of human values injected into these LLMs before their deployment and adoption. We propose UniVaR, a high-dimensional neural representation of symbolic human value distributions in LLMs, orthogonal to model architecture and training data. This is a continuous and scalable representation, self-supervised from the value-relevant output of 8 LLMs and evaluated on 15 open-source and commercial LLMs. Through UniVaR, we visualize and explore how LLMs prioritize different values in 25 languages and cultures, shedding light on complex interplay between human values and language modeling.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.07900")
get_code_for_paper("2404.07900")
have("2404.07900")

Connect an agent — have() is free.