Building Social World Models with Large Language Models
A new framework called the Social World Model (SWM) has been introduced to analyze how social beliefs evolve in response to significant events, such as policy changes and scientific breakthroughs. This model leverages large language models (LLMs) to learn state-transition functions from social data without requiring explicit human annotations or costly census data.
WPN Brief
- What Happened
A new framework called the Social World Model (SWM) has been introduced to analyze how social beliefs evolve in response to significant events, such as policy changes and scientific breakthroughs. This model leverages large language models (LLMs) to learn state-transition functions from social data without requiring explicit human annotations or costly census data.
- Why It Matters
The development of SWM is significant as it provides a systematic approach to understanding social dynamics, potentially aiding researchers and policymakers in predicting shifts in public opinion and beliefs.
- The Bigger Picture
This advancement reflects a growing trend in artificial intelligence to utilize LLMs for complex social science applications, highlighting the intersection of technology and social understanding, while also raising questions about the reliability and biases inherent in AI-driven evaluations and frameworks.
Related Reports
More coverage on this story
10 reports across the wire
REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs
A new framework called REAL has been introduced to enhance long-term memory management for Large Language Models (LLMs). This framework utilizes a temporal and confidence-aware directed property graph to represent atomic facts, addressing the limitations of existing memory systems that struggle with retaining historical interactions beyond the context window.
The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
A comprehensive survey titled 'The Periodic Table of LLM Reasoning' has been published, analyzing over 300 papers to explore the reasoning capabilities of Large Language Models (LLMs) and their failure modes. The study highlights advancements in structured inference and multi-step problem solving, while also noting inconsistencies in reasoning behavior influenced by various factors such as prompting strategies and model scale.
Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models
A new paper titled 'Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models' introduces SKIM, a method designed to compress procedural knowledge in large language models (LLMs) while preserving logical dependencies and enabling lightweight updates. This approach addresses the inefficiencies of existing text compression techniques that focus primarily on factual knowledge.
Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs
A recent study has introduced a method for removing unknown backdoors in Large Language Models (LLMs) by utilizing shared internal mechanisms across different backdoor types. This approach involves embedding a known trigger, termed a dummy backdoor, and subsequently fine-tuning the model using inputs triggered by this backdoor alongside clean responses. This technique aims to enhance the safety and reliability of LLMs against backdoor attacks.
Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning
A new framework called Task-Aware Structured Memory (TASM) has been introduced to enhance the scalability of multi-modal large language models (MLLMs) by addressing limitations in in-context learning (ICL). TASM offers a training-free solution that allows for dynamic memory construction, improving task adaptation without the biases associated with traditional memory compression methods.
On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
A systematic study has been conducted on the effectiveness-fluency trade-off in conditioning Large Language Models (LLMs), revealing that while efficient steering methods can achieve desired conditioning, they often compromise fluency. The research highlights the interaction between conditioning methods and training paradigms, noting that activation steering is less effective on instruction-tuned models compared to base models.
A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth
A new judge-aware ranking framework has been proposed for evaluating large language models (LLMs) without ground truth labels, addressing the inconsistencies in reliability among judge LLMs. This framework extends the Bradley-Terry-Luce model by incorporating judge-specific discrimination parameters, allowing for a more accurate estimation of model quality and judge reliability through pairwise comparisons.
Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey
A recent survey published on arXiv highlights the increasing importance of resource constraints in training large language models (LLMs), focusing on three key areas: data efficiency, memory efficiency, and compute budget awareness. The survey emphasizes that efficiency should be viewed as an interconnected system rather than isolated techniques.
Apertus LLM Family Expansion via Distillation and Quantization
The Apertus LLM family has expanded through the implementation of distillation and quantization techniques, resulting in the creation of Apertus-v1.1, a distilled model family with up to 4 billion parameters trained on 1.7 trillion permissive license tokens. This development addresses the growing demand for large language models (LLMs) that can operate within various hardware constraints.
Compatibility-Aware Dynamic Fine-Tuning for Large Language Models
A new approach called Compatibility-Aware Dynamic Fine-Tuning (CADFT) has been introduced to enhance the fine-tuning process of large language models (LLMs). This method addresses the challenges of optimization instability and limited generalization associated with traditional supervised fine-tuning by controlling sample-level optimization variance through a dynamic compatibility signal derived from model likelihoods.