Samuel Lewis-Lim's picture

11 8

Samuel Lewis-Lim

Samll

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 21 hours ago

Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models

upvoted a paper 7 days ago

No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding

upvoted a paper 30 days ago

An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift

View all activity

Organizations

None yet

Papers 1

arxiv:2508.19827

models 2

Samll/wild_hallu_v3-3b

Text Generation • 3B • Updated Aug 19, 2025 • 3

Samll/amazon_reviews_v2_llama3-3b

Text Generation • 3B • Updated Aug 17, 2025 • 3

datasets 20

Samll/wild_hallucinations_deepseek_factscore_chat_v2

Viewer • Updated Aug 14, 2025 • 3.65k • 5

Samll/wild_hallucinations_deepseek_factscore_chat

Viewer • Updated Aug 7, 2025 • 3.38k • 5

Samll/hotpotqa_inference_llama3-8b

Viewer • Updated Aug 6, 2025 • 20k • 1

Samll/wild_hallucinations_deepseek_factscore

Viewer • Updated Aug 5, 2025 • 1k • 3

Samll/wild_hallucinations_with_responses

Viewer • Updated Jun 19, 2025 • 7.92k • 2

Samll/Llama-3.1-8B-Instruct_attn_rollout_attributions_v1

Viewer • Updated Mar 3, 2025 • 5.77k • 3

Samll/Llama-3.1-8B-Instruct_attn_rollout_attributions

Viewer • Updated Mar 1, 2025 • 15.1k • 3

Samll/Llama-3.1-8B-Instruct_Taur_CoT_contrastive_relevances_attn_test

Viewer • Updated Feb 28, 2025 • 210 • 4

Samll/Llama-3.1-8B-Instruct_Taur_CoT_contrastive_relevances_v1

Viewer • Updated Feb 25, 2025 • 13.3k • 3

Samll/Llama-3.1-8B-Instruct_Taur_CoT_contrastive_relevances

Viewer • Updated Feb 19, 2025 • 22.4k • 11

View 20 datasets