Archiki Prasad

40 papers A* 7A 1B 1Misc 1Journal 24Unranked 6
YearRankTypeTitle / Venue / Authors
2026 J jnl
Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates.
CoRR
Duy Nguyen, Hanqi Xiao, Archiki Prasad, Elias Stengel-Eskin, Hyunji Lee, Mohit Bansal
2026 J jnl
Effective Reasoning Chains Reduce Intrinsic Dimensionality.
CoRR
Archiki Prasad, Mandar Joshi, Kenton Lee, Mohit Bansal, Peter Shaw
2025 — conf
AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge.
NAACL (Long Papers)
Han Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2025 J jnl
Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems.
CoRR
Zaid Khan, Elias Stengel-Eskin, Archiki Prasad, Jaemin Cho, Mohit Bansal
2025 J jnl
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs.
CoRR
Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2025 J jnl
Learning to Generate Unit Tests for Automated Debugging.
CoRR
Archiki Prasad, Elias Stengel-Eskin, Justin Chih-Yao Chen, Zaid Khan, Mohit Bansal
2025 A* conf
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning.
EMNLP
Justin Chih-Yao Chen, Archiki Prasad, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal
2025 — conf
Multi-Attribute Steering of Language Models via Targeted Intervention.
ACL (1)
Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2025 J jnl
Multi-Attribute Steering of Language Models via Targeted Intervention.
CoRR
Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2025 J jnl
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration.
CoRR
Zaid Khan, Archiki Prasad, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal
2025 J jnl
PRInTS: Reward Modeling for Long-Horizon Information Seeking.
CoRR
Jaewoo Lee, Archiki Prasad, Justin Chih-Yao Chen, Zaid Khan, Elias Stengel-Eskin, Mohit Bansal
2025 J jnl
Retrieval-Augmented Generation with Conflicting Evidence.
CoRR
Han Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2025 A* conf
Self-Consistency Preference Optimization.
ICML
Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang, Jing Xu, Maryam Fazel-Zarandi, Mohit Bansal, Sainbayar Sukhbaatar, Jason E. Weston, Jane Yu
2025 A* conf
System 1.x: Learning to Balance Fast and Slow Planning with Language Models.
ICLR
Swarnadeep Saha, Archiki Prasad, Justin Chih-Yao Chen, Peter Hase, Elias Stengel-Eskin, Mohit Bansal
2025 J jnl
Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression.
CoRR
Joykirat Singh, Justin Chih-Yao Chen, Archiki Prasad, Elias Stengel-Eskin, Akshay Nambi, Mohit Bansal
2024 — conf
ADaPT: As-Needed Decomposition and Planning with Language Models.
NAACL-HLT (Findings)
Archiki Prasad, Alexander Koller, Mareike Hartmann, Peter Clark, Ashish Sabharwal, Mohit Bansal, Tushar Khot
2024 J jnl
AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge.
CoRR
Han Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2024 J jnl
LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits.
CoRR
Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2024 J jnl
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning.
CoRR
Justin Chih-Yao Chen, Archiki Prasad, Swarnadeep Saha, Elias Stengel-Eskin, Mohit Bansal
2024 A* conf
ReGAL: Refactoring Programs to Discover Generalizable Abstractions.
ICML
Elias Stengel-Eskin, Archiki Prasad, Mohit Bansal
2024 J jnl
ReGAL: Refactoring Programs to Discover Generalizable Abstractions.
CoRR
Elias Stengel-Eskin, Archiki Prasad, Mohit Bansal
2024 A* conf
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models.
ICLR
Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2024 J jnl
Self-Consistency Preference Optimization.
CoRR
Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang, Jing Xu, Maryam Fazel-Zarandi, Mohit Bansal, Sainbayar Sukhbaatar, Jason Weston, Jane A. Yu
2024 J jnl
Soft Self-Consistency Improves Language Model Agents.
CoRR
Han Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2024 — conf
Soft Self-Consistency Improves Language Models Agents.
ACL (Short Papers)
Han Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2024 J jnl
System-1.x: Learning to Balance Fast and Slow Planning with Language Models.
CoRR
Swarnadeep Saha, Archiki Prasad, Justin Chih-Yao Chen, Peter Hase, Elias Stengel-Eskin, Mohit Bansal
2023 J jnl
ADaPT: As-Needed Decomposition and Planning with Language Models.
CoRR
Archiki Prasad, Alexander Koller, Mareike Hartmann, Peter Clark, Ashish Sabharwal, Mohit Bansal, Tushar Khot
2023 A conf
GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models.
EACL
Archiki Prasad, Peter Hase, Xiang Zhou, Mohit Bansal
2023 — conf
MeetingQA: Extractive Question-Answering on Meeting Transcripts.
ACL (1)
Archiki Prasad, Trung Bui, Seunghyun Yoon, Hanieh Deilamsalehy, Franck Dernoncourt, Mohit Bansal
2023 A* conf
ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness.
EMNLP
Archiki Prasad, Swarnadeep Saha, Xiang Zhou, Mohit Bansal
2023 J jnl
ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness.
CoRR
Archiki Prasad, Swarnadeep Saha, Xiang Zhou, Mohit Bansal
2023 J jnl
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models.
CoRR
Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
2022 J jnl
GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models.
CoRR
Archiki Prasad, Peter Hase, Xiang Zhou, Mohit Bansal
2021 Misc conf
An Investigation of End-to-End Models for Robust Speech Recognition.
ICASSP
Archiki Prasad, Preethi Jyothi, Rajbabu Velmurugan
2021 J jnl
An Investigation of End-to-End Models for Robust Speech Recognition.
CoRR
Archiki Prasad, Preethi Jyothi, Rajbabu Velmurugan
2021 B conf
Decentralized Age-of-Information Bandits.
WCNC
Archiki Prasad, Vishal Jain, Sharayu Moharir
2021 J jnl
The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding.
CoRR
Archiki Prasad, Mohammad Ali Rehan, Shreya Pathak, Preethi Jyothi
2020 J jnl
Decentralized Age-of-Information Bandits.
CoRR
Archiki Prasad, Vishal Jain, Sharayu Moharir
2020 A* conf
How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems.
ACL
Archiki Prasad, Preethi Jyothi
2020 — conf
Time Series Forecasting for Cold-Start Items by Learning from Related Items using Memory Networks.
WWW (Companion Volume)
Ayush Chauhan, Archiki Prasad, Parth Gupta, Prashanth Amireddy, Shiv Kumar Saini