activity
20242026
collaborators

7 papers

cs.AI2026

Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics

Stella Biderman, Mohammad Aflah Khan, Niloofar Mireshghallah +3

What would it mean to have a scientific understanding of AI? Models are not static objects: they are snapshots of time-evolving processes shaped by data, objectives, architectures,…

cs.CL2026

Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective

Bishwamittra Ghosh, Soumi Das, Till Speicher +5

Large language models (LLMs) operate in two fundamental learning modes - fine-tuning (FT) and in-context learning (ICL) - raising key questions about which mode yields greater lang…

cs.LG2026

Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE

Mohammad Aflah Khan, Krishna P. Gummadi, Manish Gupta +1

Rotary Positional Embedding (RoPE) is a common choice in transformer architectures for encoding relative positional information. Although earlier work has examined omitting RoPE in…

cs.CL2026

Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs

Qinyuan Wu, Soumi Das, Mahsa Amani +4

Rote learning is a memorization technique based on repetition. Many researchers argue that rote learning hinders generalization because it encourages verbatim memorization rather t…

cs.CL2026

In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations

Mohammad Aflah Khan, Mahsa Amani, Soumi Das +5

Agents based on Large Language Models (LLMs) are increasingly being deployed as interfaces to information on online platforms. These agents filter, prioritize, and synthesize infor…

cs.LG2025

Rethinking Memorization Measures and their Implications in Large Language Models

Bishwamittra Ghosh, Soumi Das, Qinyuan Wu +4

Concerned with privacy threats, memorization in LLMs is often seen as undesirable, specifically for learning. In this paper, we study whether memorization can be avoided when optim…