New Publication at NALOMA 2026

@inproceedings{Hammerla:Mehler:2026:b,
  title     = {Negation in Reasoning Traces: Interpretable Signals of Correctness
               and Provenance},
  author    = {Hammerla, Leon Lukas and Mehler, Alexander},
  editor    = {Yanaka, Hitomi and Abzianidze, Lasha},
  booktitle = {Proceedings of the 6th Workshop on Natural Language Meets Logic
               and Machine Learning ({NALOMA})},
  month     = {aug},
  year      = {2026},
  address   = {Prague, Czechia},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.naloma-1.4/},
  pages     = {19--39},
  isbn      = {979-8-89176-389-0},
  abstract  = {Chain-of-thought (CoT) reasoning is widely used in large language
               models (LLMs), but the resulting reasoning traces remain underexplored.We
               study these traces through the lens of discourse-level negation.Specifically,
               we distinguish between corrective negation, which rejects a prior
               reasoning step, and refining negation, which narrows or qualifies
               it, and introduce metrics to quantify their use in human- and
               LLM-authored reasoning traces.Across multiple benchmarks, we find
               that negation occurs much more frequently in intermediate reasoning
               traces than in final response texts.We then test whether negation-based
               features provide predictive and descriptive signal for correctness,
               model identity, and human-vs.-LLM authorship.For correctness prediction,
               negation-based features consistently outperform simple structural
               baselines and in several settings add complementary signal to
               embedding-based representations, although embeddings remain stronger
               overall.In a controlled comparison on correct human and LLM traces
               from the same dataset, our strongest results arise in human-vs.-LLM
               classification, where negation features outperform both structural
               and embedding baselines.Overall, these findings position discourse-level
               negation as an interpretable feature for reasoning-trace analysis,
               with especially strong utility for provenance-related classification
               and modest but consistent value for correctness prediction.}
}