Elamur Research⌕
☰
home / authors / Ansh Radhakrishnan

Ansh Radhakrishnan

Ansh Radhakrishnan has 3 papers in our library, in 2023–2025, most of them on Reasoning, Language models & pretraining; often with Carson Denison, Samuel R. Bowman, Akbir Khan.

3 papers in our library · 2023–2025

OpenAlex · h-index 6 · 7 works · 126 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 650 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #4399

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksComputer Science · 3 worksArts and Humanities · 2 worksLanguage and Linguistics · 2 worksSafety Research · 2 worksSocial Sciences · 2 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 2 worksLanguage models & pretraining · 1 work

 Works by year

2020s

20251 paper20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Measuring Faithfulness in Chain-of-Thought Reasoning (2023 · 262 citations)
    Step-by-step "Chain-of-Thought" (CoT) prompting makes LLMs more accurate. It is less clear whether the written reasoning actually explains how the model reaches its answer. The authors, mostly at Anthropic, built a set of interventions to test this. They cut the CoT short, inserted an error into it, reworded it, or…
  2. Reasoning Models Don't Always Say What They Think (2025 · 106 citations)
    Monitoring a model's chain-of-thought (CoT) is often proposed as a safety tool. It only works if the written reasoning reflects what actually drives the answer. The authors examine this using Claude 3.7 Sonnet and DeepSeek R1, both of which perform explicit reasoning, and set them against the non-reasoning Claude 3.5…
  3. Debating with More Persuasive LLMs Leads to More Truthful Answers (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.

All works

5 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

  1. Measuring Faithfulness in Chain-of-Thought ReasoningarXiv:2307.13702Tamera Lanham, Anna Chen, Ansh Radhakrishnan, et al.2023 · 262 citations
  2. Many-shot Jailbreaking ↗neural information processing systems · no summary yetCem Anil et al.2024 · 109 citations
  3. Reasoning Models Don't Always Say What They ThinkarXiv:2505.05410Yanda Chen, Joe Benton, Ansh Radhakrishnan, et al.2025 · 106 citations
  4. Debating with More Persuasive LLMs Leads to More Truthful AnswersarXiv:2402.06782Akbir Khan, John Hughes, Dan Valentine, et al.2024 · 101 citations
  5. Question Decomposition Improves the Faithfulness of Model-Generated Reasoning ↗arXiv (Cornell University) · no summary yetAnsh Radhakrishnan et al.2023 · 74 citations

 Co-authors here

12 of 22 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 650 times (of the 149,439 papers whose bibliographies we read); 150 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ansh-radhakrishnan/