--- title: "Akbir Khan — author profile and papers — Elamur Research" description: "Akbir Khan, University College London: 2 papers on Elamur Research (2022–2024), h-index 6 — affiliations, topics, co-authors and who cites…" canonical: "https://research.elamur.ai/free/en/authors/akbir-khan/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/akbir-khan/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Akbir Khan # Akbir Khan Akbir Khan has 2 papers in our library, in 2022–2024, most of them on [Implicature](https://md.research.elamur.ai/free/en/topics/implicature/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Edward Grefenstette](https://md.research.elamur.ai/free/en/authors/edward-grefenstette/), [Laura Ruis](https://md.research.elamur.ai/free/en/authors/laura-ruis/), [Tim Rocktaschel](https://md.research.elamur.ai/free/en/authors/tim-rocktaschel/). 2 papers in our library · 2022–2024 [OpenAlex](https://openalex.org/A5084386381) · [**h-index 6**](https://openalex.org/authors/A5084386381) · [23 works](https://openalex.org/works?filter=author.id:A5084386381) · [110 citations](https://openalex.org/works?filter=author.id:A5084386381&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/akbir-khan/#papers) · [🔗 Cited 251 times in our library](https://md.research.elamur.ai/free/en/authors/akbir-khan/cited-by/) · [3 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #6612](https://md.research.elamur.ai/free/en/paper-stars/page/67/#star-6612) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Akbir+Khan) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Akbir+Khan) · [dblp](https://dblp.org/search?q=Akbir+Khan) · [ACL Anthology](https://aclanthology.org/search/?q=Akbir+Khan) ## Affiliations [🎓**University College London** London · United Kingdom 2023–2025 · 7 papers*current*](https://md.research.elamur.ai/free/en/universities/university-college-london/) · [🏢**Anthropic** San Francisco · United States 2024 · 3 papers](https://md.research.elamur.ai/free/en/companies/anthropic/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Safety Research · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/) 🧭 Topics 2 Research subjects and languages the work is about.[Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) · [Implicature · 1 work](https://md.research.elamur.ai/free/en/topics/implicature/) 💡 Concepts 1 Key ideas and methods explained on our concept pages.[Implicature · 1 work](https://md.research.elamur.ai/free/en/concepts/implicature/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/akbir-khan/year/2024/) · [**2022** 1 paper](https://md.research.elamur.ai/free/en/authors/akbir-khan/year/2022/) ## Papers The most cited first (OpenAlex and our library). 1. **[Debating with More Persuasive LLMs Leads to More Truthful Answers](https://md.research.elamur.ai/free/en/papers/khan-2024-debating-more-persuasive-llms-leads/)** *(2024 · 101 citations)* The paper asks whether weaker overseers can reliably check stronger AI systems, a problem that grows as models outpace human expertise and ground-truth labels become unavailable. 2. **[The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs](https://md.research.elamur.ai/free/en/papers/ruis-2022-goldilocks-pragmatic-understanding-fine-tuning/)** *(2022 · 86 citations)* The authors test whether large language models (LLMs) can understand conversational implicature, that is, an indirect answer. ## All works 5 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them. 1. [**Debating with More Persuasive LLMs Leads to More Truthful Answers arXiv:2402.06782**Akbir Khan, John Hughes, Dan Valentine, et al.*2024 · 101 citations*](https://md.research.elamur.ai/free/en/papers/khan-2024-debating-more-persuasive-llms-leads/) 2. **[The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs](https://md.research.elamur.ai/free/en/papers/ruis-2022-goldilocks-pragmatic-understanding-fine-tuning/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Laura Ruis, Akbir Khan, Stella Biderman, et al.*2022 · 86 citations* 3. **[Alignment faking in large language models ↗](https://arxiv.org/abs/2412.14093) arXiv (Cornell University) · no summary yet**Ryan Greenblatt et al.*2024 · 82 citations* 4. **[Language Models Learn to Mislead Humans via RLHF ↗](https://arxiv.org/abs/2409.12822) arXiv (Cornell University) · no summary yet**Jiaxin Wen et al.*2024 · 33 citations* 5. **[Auditing language models for hidden objectives ↗](https://arxiv.org/abs/2503.10965) arXiv (Cornell University) · no summary yet**Marks, Samuel et al.*2025 · 19 citations* ## Co-authors here 9 co-authors with a page, the most papers together first. - [Edward Grefenstette](https://md.research.elamur.ai/free/en/authors/edward-grefenstette/) ×2 - [Laura Ruis](https://md.research.elamur.ai/free/en/authors/laura-ruis/) ×2 - [Tim Rocktaschel](https://md.research.elamur.ai/free/en/authors/tim-rocktaschel/) ×2 - [Ansh Radhakrishnan](https://md.research.elamur.ai/free/en/authors/ansh-radhakrishnan/) - [Ethan Perez](https://md.research.elamur.ai/free/en/authors/ethan-perez/) - [John Hughes](https://md.research.elamur.ai/free/en/authors/john-hughes/) - [Samuel R. Bowman](https://md.research.elamur.ai/free/en/authors/samuel-r-bowman/) - [Sara Hooker](https://md.research.elamur.ai/free/en/authors/sara-hooker/) - [Stella Biderman](https://md.research.elamur.ai/free/en/authors/stella-biderman/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/): [NeurIPS 2022](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2022/) ## Cited by Papers of our library cite their works 251 times (of the 149,439 papers whose bibliographies we read); [68 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/akbir-khan/cited-by/). Updated 2 November 2026