Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data
Zesheng Shi, Xue Li, Chenrui Dai +1
LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate directives with adversarial prompt injections, and the model m…
cs.CL2026
Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time
Zeen Zhu, Zhuo Li, Weiyang Guo +4
A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we identify a structural mismatc…
cs.CL2026
Mining or Synthesis? Rethinking Exploration Efficiency in Iterative Alignment of Mathematical Reasoning
Jun Rao, Zixiong Yu, Xuebo Liu +6
Iterative Direct Preference Optimization (DPO) has emerged as a widely used paradigm for aligning Large Language Models on reasoning tasks. Existing approaches typically rely on Be…