--- title: "Hannaneh Hajishirzi — papers, page 3 · University of Washington" description: "Hannaneh Hajishirzi, University of Washington: 59 papers on Elamur Research (2013–2025), h-index 61 — affiliations, topics, co-authors and…" canonical: "https://research.elamur.ai/free/en/authors/hannaneh-hajishirzi/page/3/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/hannaneh-hajishirzi/page/3/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Hannaneh Hajishirzi](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/) / page 3 # Hannaneh Hajishirzi · page 3 59 papers in our library · 2013–2025 · page 3 of 3 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/page/2/) [1](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/) [2](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/page/2/) **3** 51. **[NaturalProver: Grounded Mathematical Proof Generation with Language Models](https://md.research.elamur.ai/free/en/papers/welleck-2022-naturalprover-grounded-mathematical-proof-generation/)** *(2022 · 62 citations)* The paper tackles theorem proving in informal mathematics, where proofs mix prose and LaTeX, a setting that modern generative models had barely explored. 52. **[Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks](https://md.research.elamur.ai/free/en/papers/asai-2022-evidentiality-guided-generation-knowledge-intensive/)** *(2022 · 60 citations)* Retrieval-augmented generators such as FiD often produce answers from retrieved passages that look relevant but do not actually support the output. 53. **[Generalizing Verifiable Instruction Following](https://md.research.elamur.ai/free/en/papers/pyatkin-2025-generalizing-verifiable-instruction-following/)** *(2025 · 59 citations)* Language models are commonly tested on whether they obey checkable output rules, such as word counts or required formats. 54. **[Spurious Rewards: Rethinking Training Signals in RLVR](https://md.research.elamur.ai/free/en/papers/shao-2025-spurious-rewards-rethinking-training-signals/)** *(2025 · 53 citations)* Reinforcement learning with verifiable rewards (RLVR) is credited with improving math reasoning in language models, but it is unclear what in the training signal actually causes the gains. 55. **[Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://md.research.elamur.ai/free/en/papers/ivison-2024-unpacking-dpo-ppo-disentangling-best/)** *(2024 · 50 citations)* Preference-based training is now a standard final stage for language models. Published setups, however, combine different datasets, algorithms and evaluation suites, so it is unclear which ingredient actually drives the gains. The authors divide the pipeline into four components: preference data, the learning… 56. **[Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding](https://md.research.elamur.ai/free/en/papers/liu-2023-don-t-throw-away-value/)** *(2023 · 46 citations)* Language models aligned with PPO are usually deployed using only the policy network. The value network that PPO trains alongside it is typically thrown away. The authors argue that this byproduct is well suited to scoring candidates during guided decoding. It is trained to estimate the expected return of unfinished… 57. **[Reliable, Adaptable, and Attributable Language Models with Retrieval](https://md.research.elamur.ai/free/en/papers/asai-2024-reliable-adaptable-attributable-language-models/)** *(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… 58. **[Probing Contextual Language Models for Common Ground with Visual Representations](https://md.research.elamur.ai/free/en/papers/ilharco-2021-probing-contextual-language-models-common/)** *(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. 59. **[InSCIt: Information-Seeking Conversations with Mixed-Initiative Interactions](https://md.research.elamur.ai/free/en/papers/wu-2023-inscit-information-seeking-conversations-mixed/)** *(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… [← prev](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/page/2/) [1](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/) [2](https://md.research.elamur.ai/free/en/authors/hannaneh-hajishirzi/page/2/) **3**