作者位次 #2/3ACL 2026Poster· Natural Language Processing
Challenging the Explanation Based on Preceding Tokens: Discovering Transferable Non-Literal Biasing
Yuchen Huang · Junpeng Zhang · Quanshi Zhang
摘要
In this paper, we find that the generated preceding tokens, which are not directly related to the answer, may still significantly push the large language model (LLM) towards the target answer. More crucially, the biased connotations of target answer in the preceding tokens can also transfer to ot...
社会与人本OpenReview 项目页