From the 1 of 14 linked papers with an AI index.
14 papers
Token-Level Diagnosis of Sycophancy in LLMs with Attribution-Guided Steering
Hieu Nguyen, Mahammed Kamruzzaman, Anshuman Chhabra +1
Sycophancy refers to the tendency for large language models (LLMs) to match user beliefs at the cost of factual correctness, thereby undermining model reliability. Prior work on ev…
Implicit Reasoning Steering via Concept Chaining
Xiao Ye, Sanika Chavan, Yuxi Huang +4
The paper introduces Concept Chaining, a method that creates short natural-language paragraphs linking question entities to a target answer via intermediate concepts, and uses cont…
Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization
Theophilus Amaefuna, Hitesh Vaidya, Anshuman Chhabra +1
Layer-wise capacity in large language models is highly non-uniform: some layers contribute disproportionately to loss reduction, whereas others are nearly redundant. Existing layer…
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Advik Raj Basani, Anshuman Chhabra
Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly retraining, but its reliability and underlying mechanisms remain poorly understo…
Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling
Ocean Monjur, Shahriar Kabir Nahin, Anshuman Chhabra
Large Language Models (LLMs) now exhibit remarkable reasoning capabilities through test-time compute scaling (TTS), with impressive performance across math and coding benchmarks. I…
AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models
Tadesse Destaw Belay, Shahriar Kabir Nahin, Israel Abebe Azime +6
How can language learning systems be developed for languages that lack sufficient training resources? This challenge is increasingly faced by developers across the African continen…