List your company

Table Question Answering on WTQ (Evaluation Set)

47Alignment ScoreLLAMA-3.1-8B-INST
4.3615.4326.537.57May 1, 2026

Evaluation results

MethodLinks
LLAMA-3.1-8B-INSTInput Protocol=Vanilla2026.0547
QWEN2.5-14B-INSTInput Protocol=Vanilla2026.0547
TABLELLM-8BInput Protocol=Vanilla2026.0533
QWEN2.5-14B-INSTInput Protocol=Rand Perm2026.0533
LLAMA-3.1-8B-INSTInput Protocol=Rand Perm2026.0531
QWEN2.5-7B-INSTInput Protocol=Vanilla2026.0529
LLAMA-3.1-8BInput Protocol=Vanilla2026.0526
QWEN2.5-14B-INSTInput Protocol=ATP Attack2026.0526
TABLELLM-8BInput Protocol=Rand Perm2026.0523
DS-R1-DIST-LLAMA-8BInput Protocol=Vanilla2026.0523
LLAMA-3.1-8B-INSTInput Protocol=ATP Attack2026.0522
QWEN2.5-7B-INSTInput Protocol=Rand Perm2026.0521
CODELLAMA-7B-INSTInput Protocol=Vanilla2026.0518
LLAMA-3.1-8BInput Protocol=Rand Perm2026.0517
TABLELLM-8BInput Protocol=ATP Attack2026.0516
CODELLAMA-7B-INSTInput Protocol=Rand Perm2026.0516
DS-R1-DIST-LLAMA-8BInput Protocol=Rand Perm2026.0515
DS-R1-DIST-QWEN-7BInput Protocol=Vanilla2026.0514
LLAMA-3.1-8BInput Protocol=ATP Attack2026.0513
QWEN2.5-7B-INSTInput Protocol=ATP Attack2026.0512
DS-R1-DIST-QWEN-7BInput Protocol=Rand Perm2026.0512
CODELLAMA-7B-INSTInput Protocol=ATP Attack2026.059
DS-R1-DIST-LLAMA-8BInput Protocol=ATP Attack2026.059
DS-R1-DIST-QWEN-7BInput Protocol=ATP Attack2026.056