Related papers: Dialz: A Python Toolkit for Steering Vectors

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…

Large Language Models (LLMs) have become powerful tools for annotating unstructured data. However, most existing workflows rely on ad hoc scripts, making reproducibility, robustness, and systematic evaluation difficult. To address these…

We present ADVISER - an open-source, multi-domain dialog system toolkit that enables the development of multi-modal (incorporating speech, text and vision), socially-engaged (e.g. emotion recognition, engagement level prediction and…

Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning seems to be a direct solution, it requires substantial…

The increasing amount of available data, computing power, and the constant pursuit for higher performance results in the growing complexity of predictive models. Their black-box nature leads to opaqueness debt phenomenon inflicting…

This paper discusses our proposal and implementation of Distill, a domain-specific compilation tool based on LLVM to accelerate cognitive models. Cognitive models explain the process of cognitive function and offer a path to human-like…

Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate human behavior remains a significant challenge. An effective simulator must expose the failure…

We present SDialog, an MIT-licensed open-source Python toolkit that unifies dialog generation, evaluation and mechanistic interpretability into a single end-to-end framework for building and analyzing LLM-based conversational agents. Built…

We present SDialog, an MIT-licensed open-source Python toolkit that unifies dialog generation, evaluation and mechanistic interpretability into a single end-to-end framework for building and analyzing LLM-based conversational agents. Built…

The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. Steering abstractions are designed around four model control surfaces: input (modification of the prompt), structural (modification of the…

Large language models (LLMs) have shown remarkable success in recent years, enabling a wide range of applications, including intelligent assistants that support users' daily life and work. A critical factor in building such assistants is…

Current model testing work has mostly focused on creating test cases. Identifying what to test is a step that is largely ignored and poorly supported. We propose Weaver, an interactive tool that supports requirements elicitation for guiding…

Large Language Models (LLMs) are important tools for reasoning and problem-solving, while they often operate passively, answering questions without actively discovering new ones. This limitation reduces their ability to simulate human-like…

With the emergence of large language models (LLMs) as a powerful class of generative artificial intelligence (AI), their use in tutoring has become increasingly prominent. Prior works on LLM-based tutoring typically learn a single tutor…

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…

Large Language Models (LLMs) have been observed to exhibit bias in numerous ways, potentially creating or worsening outcomes for specific groups identified by protected attributes such as sex, race, sexual orientation, or age. To help…

In recent years, large language models (LLMs) have had great success in tasks such as casual conversation, contributing to significant advancements in domains like virtual assistance. However, they often generate responses that are not…

In this paper, we introduce EasyEdit2, a framework designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. EasyEdit2 supports a wide range of test-time interventions, including safety, sentiment,…

The study of complex many-body systems via analysis of the trajectories of the units that dynamically move and interact within them is a non-trivial task. The workflow for extracting meaningful information from the raw trajectory data is…

Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often struggle to produce proteins with precisely specified…