8 papers
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet +3
AI agents acting on behalf of users are constantly making decisions, and for users to trust their agents, those decisions must align with what they actually want. Privacy is an imp…
Unifying Adversarial Robustness and Training Across Text Scoring Models
Manveer Singh Tamber, Hosna Oyarhoseini, Jimmy Lin
Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying t…
Illusions of Relevance: Arbitrary Content Injection Attacks Deceive Retrievers, Rerankers, and LLM Judges
Manveer Singh Tamber, Jimmy Lin
This work considers a black-box threat model in which adversaries attempt to propagate arbitrary non-relevant content in search. We show that retrievers, rerankers, and LLM relevan…
Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
Manveer Singh Tamber, Forrest Sheng Bao, Chenyu Xu +7
Retrieval-augmented generation (RAG) aims to reduce hallucinations by grounding responses in external context, yet large language models (LLMs) still frequently introduce unsupport…
Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh +1
We investigate improving the retrieval effectiveness of embedding models through the lens of corpus-specific fine-tuning. Prior work has shown that fine-tuning with queries generat…
Can't Hide Behind the API: Stealing Black-Box Commercial Embedding Models
Manveer Singh Tamber, Jasper Xian, Jimmy Lin
Embedding models that generate dense vector representations of text are widely used and hold significant commercial value. Companies such as OpenAI and Cohere offer proprietary emb…