Featured

We conduct the first comprehensive analysis to explore language models’ (LMs) memorization during fine-tuning across tasks. Our studies indicate that memorization presents a strong disparity among different finetuning tasks.

We propose MAIR (Massive Instructed Retrieval Benchmark), a heterogeneous IR benchmark that includes 126 distinct IR tasks across 6 domains, collected from existing datasets. We benchmark state-of-the-art instruction-tuned text embedding models and re-ranking models.

We conduct extensive empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database. We further reveal that RAG can mitigate the leakage of the LLMs’ training data.

We propose an unsupervised alignment method, namely Reinforcement Learning from Contrastive Feedback (RLCF), empowering LLMs to generate both high-quality and context-specific responses.

We propose a novel zero-shot query expansion framework utilizing both LLM-generated and retrieved documents.

We propose a semantics-based watermark framework SemaMark. It leverages the semantics as an alternative to simple hashes of tokens since the paraphrase will likely preserve the semantic meaning of the sentences.

We incorporate implicit interaction into dual-encoders, and propose I^3 retriever. In particular, our implicit interaction paradigm leverages generated pseudo-queries to simulate query-passage interaction, which jointly optimizes with query and passage encoders in an end-to-end manner.

We focus on ranking user satisfaction rather than relevance in web search, and propose a PLM-based framework, namely SAT-Ranker, which comprehensively models different dimensions of user satisfaction in a unified manner.