21 citations · 25 across the 13 of their papers we have counts for
13 papers
Trove: A Flexible Toolkit for Dense Retrieval
Reza Esfandiarpoor, Max Zuo, Stephen H. Bach
We introduce Trove, an easy-to-use open-source retrieval toolkit that simplifies research experiments without sacrificing flexibility or speed. For the first time, we introduce eff…
Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
Zheng-Xin Yong, Stephen H. Bach
We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoni…
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools
Reza Esfandiarpoor, Vishwas Suryanarayanan, Stephen H. Bach +2
Since the introduction of the Model Context Protocol (MCP), the number of available tools for Large Language Models (LLMs) has increased significantly. These task-specific tool set…
Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
Yik Siu Chan, Zheng-Xin Yong, Stephen H. Bach
Reasoning language models improve performance on complex tasks by generating long chains of thought (CoTs), but this process can also increase harmful outputs in adversarial settin…
The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It
Zheng-Xin Yong, Beyza Ermis, Marzieh Fadaee +2
This paper presents a comprehensive analysis of the linguistic diversity of LLM safety research, highlighting the English-centric nature of the field. Through a systematic review o…
Crosslingual Reasoning through Test-Time Scaling
Zheng-Xin Yong, M. Farid Adilazuarda, Jonibek Mansurov +7
Reasoning capabilities of large language models are primarily studied for English, even when pretrained models are multilingual. In this work, we investigate to what extent English…
Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance
Reza Esfandiarpoor, George Zerveas, Ruochen Zhang +3
Although synthetic data has changed various aspects of information retrieval (IR) pipelines, the main training paradigm remains: contrastive learning with binary relevance labels,…
Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages
Max Zuo, Francisco Piedrahita Velez, Xiaochen Li +2
Recent works have explored using language models for planning problems. One approach examines translating natural language descriptions of planning tasks into structured planning l…
Preference Tuning For Toxicity Mitigation Generalizes Across Languages
Xiaochen Li, Zheng-Xin Yong, Stephen H. Bach
Detoxifying multilingual Large Language Models (LLMs) has become crucial due to their increasing global use. In this work, we explore zero-shot cross-lingual generalization of pref…
If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
Reza Esfandiarpoor, Cristina Menghini, Stephen H. Bach
Recent works often assume that Vision-Language Model (VLM) representations are based on visual attributes like shape. However, it is unclear to what extent VLMs prioritize this inf…
LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons
Zheng-Xin Yong, Cristina Menghini, Stephen H. Bach
Data scarcity in low-resource languages can be addressed with word-to-word translations from labeled task data in high-resource languages using bilingual lexicons. However, bilingu…
Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
Reza Esfandiarpoor, Stephen H. Bach
A promising approach for improving the performance of vision-language models like CLIP for image classification is to extend the class descriptions (i.e., prompts) with related att…
Low-Resource Languages Jailbreak GPT-4
Zheng-Xin Yong, Cristina Menghini, Stephen H. Bach
AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content. Our work exposes the inherent cross-lingual vulnerabil…