activity
20202026
collaborators
Showing cs.CLShow all

14 papers · 1 filter

cs.CL2026

Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty

Joykirat Singh, Zaid Khan, Archiki Prasad +5

Large language models (LLMs) are increasingly deployed on long-horizon tasks in partially observable environments, where they must act while inferring and tracking a complex enviro…

cs.CL2026

Effective Reasoning Chains Reduce Intrinsic Dimensionality

Archiki Prasad, Mandar Joshi, Kenton Lee +2

Chain-of-thought (CoT) reasoning and its variants have substantially improved the performance of language models on complex reasoning tasks, yet the precise mechanisms by which dif…

cs.CL2025

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin +1

Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at t…

cs.CL20252 cited

Retrieval-Augmented Generation with Conflicting Evidence

Han Wang, Archiki Prasad, Elias Stengel-Eskin +1

Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses. However, in practice, these systems…

cs.CL2025

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems

Zaid Khan, Elias Stengel-Eskin, Archiki Prasad +2

Scientists often infer abstract procedures from specific instances of problems and use the abstractions to generate new, related instances. For example, programs encoding the forma…

cs.CL2025

Multi-Attribute Steering of Language Models via Targeted Intervention

Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin +1

Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by inte…