ND
Nouha Dziri
cs.CLcs.AIcs.LGcs.CYcs.HCcs.CVcs.IRcs.MAcs.SE
On Valency
published · living versionsW_pf26rsgq·v1 · currentpublished
Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research
with Yue Huang, Zhangchen Xu, Xiaonan Luo, Zheyuan Liu +14
1 version
Preprints & journals
44 papers in the corpus · 2018–2026Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research2610.24944v1 · Yue Huang, Zhangchen Xu, Xiaonan Luo et al.2026 · 0 citationsarXivon Valency
Scaling Inference-Time Compute with Teams of Coding Agents2610.17471v1 · Keenan Samway, Daniel D'souza, Omar Darwiche Domingues et al.2026 · 0 citationsarXiv
TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities2603.16759v1 · Victoria Graf, Valentina Pyatkin, Nouha Dziri et al.2026 · 0 citationsarXiv
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)2510.22954v2 · Liwei Jiang, Yuanjun Chai, Margaret Li et al.2025 · 7 citationsarXiv
RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?2509.21016v2 · Yiyou Sun, Yuhan Cao, Pohao Huang et al.2025 · 0 citationsarXiv
OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety2507.06134v2 · Sanidhya Vijayvargiya, Aditya Bharat Soni, Xuhui Zhou et al.2025 · 0 citationsarXiv
A Different Approach to AI Safety: Proceedings from the Columbia Convening on Openness in Artificial Intelligence and AI Safety2506.22183v1 · Camille Francois, Ludovic P'eran, Ayah Bdeir et al.2025 · 0 citationsarXiv
OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization2506.18880v1 · Yiyou Sun, Shawn Hu, Georgia Zhou et al.2025 · 2 citationsarXiv
Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis2505.17636v1 · Jonathan Bennion, Shaona Ghosh, Mantek Singh et al.2025 · 0 citationsComputer Science & Information Technology 15 (2025) 27 - 39
Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?2504.11741v2 · Yiyou Sun, Georgia Zhou, Haoyue Bai et al.2025 · 0 citationsarXiv
On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective2502.14296v5 · Yue Huang, Chujie Gao, Siyuan Wu et al.2025 · 1 citationarXiv
2 OLMo 2 Furious2501.00656v3 · Team OLMo, Pete Walsh, Luca Soldaini et al.2024 · 2 citationsarXiv
Multi-Attribute Constraint Satisfaction via Language Model Rewriting2412.19198v1 · Ashutosh Baheti, Debanjana Chakraborty, Faeze Brahman et al.2024 · 0 citationsarXiv
Tulu 3: Pushing Frontiers in Open Language Model Post-Training2411.15124v5 · Nathan Lambert, Jacob Morrison, Valentina Pyatkin et al.2024 · 12 citationsarXiv
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior2410.16665v3 · Jing-Jing Li, Valentina Pyatkin, Max Kleiman-Weiner et al.2024 · 0 citationsarXiv
To Err is AI : A Case Study Informing LLM Flaw Reporting Practices2410.12104v1 · Sean McGregor, Allyson Ettinger, Nick Judd et al.2024 · 7 citationsarXiv
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction2410.08134v1 · Jarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng et al.2024 · 2 citationsarXiv
AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text2410.04265v2 · Ximing Lu, Melanie Sclar, Skyler Hallinan et al.2024 · 2 citationsarXiv
Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance2407.07950v2 · Kaitlyn Zhou, Jena D. Hwang, Xiang Ren et al.2024 · 13 citationsarXiv
The Art of Saying No: Contextual Noncompliance in Language Models2407.12043v2 · Faeze Brahman, Sachin Kumar, Vidhisha Balachandran et al.2024 · 8 citationsarXiv
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs2406.18495v3 · Seungju Han, Kavel Rao, Allyson Ettinger et al.2024 · 36 citationsarXiv
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models2406.18510v1 · Liwei Jiang, Kavel Rao, Seungju Han et al.2024 · 17 citationsarXiv
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild2406.04770v2 · Bill Yuchen Lin, Yuntian Deng, Khyathi Chandu et al.2024 · 4 citationsarXiv
RewardBench: Evaluating Reward Models for Language Modeling2403.13787v2 · Nathan Lambert, Valentina Pyatkin, Jacob Morrison et al.2024 · 17 citationsarXiv
A Roadmap to Pluralistic Alignment2402.05070v3 · Taylor Sorensen, Jared Moore, Jillian Fisher et al.2024 · 23 citationsarXiv
The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning2312.01552v1 · Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu et al.2023 · 11 citationsarXiv
The Generative AI Paradox: "What It Can Create, It May Not Understand"2311.00059v1 · Peter West, Ximing Lu, Nouha Dziri et al.2023 · 14 citationsarXiv
What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations2310.15431v2 · Kavel Rao, Liwei Jiang, Valentina Pyatkin et al.2023 · 3 citationsarXiv
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement2310.08559v4 · Linlu Qiu, Liwei Jiang, Ximing Lu et al.2023 · 4 citationsarXiv
Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties2309.00779v2 · Taylor Sorensen, Liwei Jiang, Jena Hwang et al.2023 · 32 citationsVol. 38 No. 18: AAAI-24 Technical Tracks 18; 2024; 19937-19947
Fine-Grained Human Feedback Gives Better Rewards for Language Model Training2306.01693v2 · Zeqiu Wu, Yushi Hu, Weijia Shi et al.2023 · 51 citationsarXiv
Faith and Fate: Limits of Transformers on Compositionality2305.18654v3 · Nouha Dziri, Ximing Lu, Melanie Sclar et al.2023 · 124 citationsarXiv
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning2305.15065v2 · Ximing Lu, Faeze Brahman, Peter West et al.2023 · 7 citationsarXiv
Evaluating Open-Domain Question Answering in the Era of Large Language Models2305.06984v3 · Ehsan Kamalloo, Nouha Dziri, Charles L. A. Clarke et al.2023 · 120 citationsarXiv
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation2303.17574v1 · Nico Daheim, Nouha Dziri, Mrinmaya Sachan et al.2023 · 7 citationsarXiv
Self-Refine: Iterative Refinement with Self-Feedback2303.17651v2 · Aman Madaan, Niket Tandon, Prakhar Gupta et al.2023 · 758 citationsarXiv
CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos2303.09713v2 · Seungju Han, Jack Hessel, Nouha Dziri et al.2023 · 9 citationsarXiv
FaithDial: A Faithful Benchmark for Information-Seeking Dialogue2204.10757v3 · Nouha Dziri, Ehsan Kamalloo, Sivan Milton et al.2022 · 63 citationsarXiv
On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?2204.07931v1 · Nouha Dziri, Sivan Milton, Mo Yu et al.2022 · 125 citationsarXiv
Decomposed Mutual Information Estimation for Contrastive Representation Learning2106.13401v1 · Alessandro Sordoni, Nouha Dziri, Hannes Schulz et al.2021 · 16 citationsarXiv
Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark2105.00071v3 · Nouha Dziri, Hannah Rashkin, Tal Linzen et al.2021 · 47 citationsarXiv
Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding2104.08455v2 · Nouha Dziri, Andrea Madotto, Osmar Zaiane et al.2021 · 81 citationsarXiv
Evaluating Coherence in Dialogue Systems using Entailment1904.03371v2 · Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson et al.2019 · 93 citationsarXiv
Augmenting Neural Response Generation with Context-Aware Topical Attention1811.01063v2 · Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson et al.2018 · 77 citationsarXiv
Career total: 56 works. 44 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.