Hannaneh Hajishirzi · page 3

53 papers in our library · 2013–2025 · page 3 of 3

Papers

The most cited first (OpenAlex and our library).

Reliable, Adaptable, and Attributable Language Models with Retrieval (2024 · 45 citations)
This position paper by Asai et al. contends that retrieval-augmented LMs should succeed purely parametric LMs as the main design for future language models. It contains no new experiments, datasets, or models. Instead, it surveys prior work and lists five weaknesses of parametric models: hallucinated facts, outputs…
Probing Contextual Language Models for Common Ground with Visual Representations (2021 · 33 citations)
The paper asks how far text-only contextual language models encode information that lines up with visual representations of concrete nouns, without any visual supervision during pre-training.
InSCIt: Information-Seeking Conversations with Mixed-Initiative Interactions (2023 · 23 citations)
Conversational QA systems usually assume each user question has one direct answer in a single passage. Real users, however, often ask vague or unanswerable questions, and a helpful agent should sometimes take the lead by asking for clarification or offering related partial information. Existing datasets rarely…