Metraipolis › archive › dc_6263798b6397

Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection — arXiv:2608.29066

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.29066
License (as archived): CC0-1.0
Archived: 2026-10-17T07:47:28.184Z
SHA-256 of the archived text: ae82dae57db34676c8847e656db9fbaefd3b2e626614b3c5038ded07903d2eb9
Stable URL of this page: https://metraipolis.com/documento/dc_6263798b6397

How to cite

Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection — arXiv:2608.29066 — arXiv (en), https://arxiv.org/abs/2608.29066 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6263798b6397 (Metraipolis archive dc_6263798b6397, sha256 ae82dae57db34676c8847e656db9fbaefd3b2e626614b3c5038ded07903d2eb9)

BibTeX

@misc{dc6263798b6397,
  title = {Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection — arXiv:2608.29066},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29066},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6263798b6397; sha256 ae82dae57db34676c8847e656db9fbaefd3b2e626614b3c5038ded07903d2eb9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29066. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Stance detection is crucial for understanding the underlying attitude of an expression towards a target. Conversational stance detection is a more challenging stance detection task in real-world social media scenarios, as it involves detecting the user's stance by leveraging the target-related historical statements across conversational sessions. In this paper, we propose target-aware Memory Graph TamGraph, a novel method that dynamically leverages target-related statements for conversational stance detection. Instead of considering all preceding historical conversations or using no prior conversation information for stance detection, our TamGraph employs a stepwise, entropy-guided backtracking mechanism to selectively activate memory from historical conversations and dynamically constructs a target-aware graph to model the stance relations among utterances. This allows the exploitation of target-related information from the conversation history for stance detection while preventing the introduction of noise. Experimental results on both English and Chinese benchmarks demonstrate that our TamGraph substantially improves LLM performance on conversational stance detection.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.29066 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:28:26.715Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).