19 papers
Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models
Ruta Binkyte, Ivaxi Sheth, Zhijing Jin +3
Ensuring trustworthiness in machine learning (ML) systems is crucial as they become increasingly embedded in high-stakes domains. This paper advocates for integrating causal method…
Test of Time: Rethinking Temporal Signal of Benchmark Contamination
Terry Jingchen Zhang, Gopal Dev, Ning Wang +8
Post-cutoff performance decay of LLMs has been widely interpreted as a temporal signal for benchmark contamination, where public information released before the training cutoff may…
Can Theoretical Physics Research Benefit from Language Agents?
Sirui Lu, Zhijing Jin, Terry Jingchen Zhang +3
Large Language Models (LLMs) are rapidly advancing across diverse domains, yet their application in theoretical physics remains inadequate. While current models show competence in…
When Do Language Models Endorse Limitations on Human Rights Principles?
Keenan Samway, Nicole Miu Takagi, Rada Mihalcea +4
As Large Language Models (LLMs) increasingly mediate global information access with the potential to shape public discourse, their alignment with universal human rights principles…
Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards
Punya Syon Pandey, Samuel Simko, Kellin Pelrine +1
As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern. While fine-tuning models on domain-specific datasets is of…
Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders
Abir Harrasse, Florent Draye, Punya Syon Pandey +2
Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representat…