Search Results for author:
Found 12 papers, 2 papers with code
Programming Refusal with Conditional Activation Steering
In this paper, we propose Conditional Activation Steering (CAST), which analyzes LLM activation patterns during inference to selectively apply or withhold activation steering based on the input context.
Value Alignment from Unstructured Text
Aligning large language models (LLMs) to value systems has emerged as a significant area of research within the fields of AI and NLP.
When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails
Motivated by findings from developing a detector for social bias, we adopt the notion of a use-mention distinction - which we identified as the primary source of under-performance in the preliminary versions of our social bias detector.
The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers
Evaluation of large language models (LLMs) for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), which measure the ability of LLMs to generate complete code that passes unit tests.
Language Models in Dialogue: Conversational Maxims for Human-AI Interactions
Modern language models, while sophisticated, exhibit some inherent shortcomings, particularly in conversational settings.
Multi-Level Explanations for Generative Language Models
To address the challenges of text as output and long text inputs, we propose a general framework called MExGen that can be instantiated with different attribution algorithms.
Contextual Moral Value Alignment Through Context-Based Aggregation
Developing value-aligned AI agents is a complex undertaking and an ongoing challenge in the field of AI.
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models
Current datasets for unwanted social bias auditing are limited to studying protected demographic features such as race and gender.
Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions
In this paper, focusing specifically on compositions of functions arising from the different pillars, we aim to reduce this gap, develop new insights for trustworthy ML, and answer questions such as the following.
Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
Recent years have seen the development of many open-source ML fairness toolkits aimed at helping ML practitioners assess and address unfairness in their systems.
A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms
This stylized setup offers the distinct capability of testing fairness interventions beyond observational data and against an unbiased benchmark.
