Xiao Zhang, Jun Xu, Ji-Rong Wen, Gang Wang, Haoyu Wang, Zhenhua Dong, Liang Pang, Sunhao Dai, Haiyuan Zhao
We lifted 3 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| whydwelledonai/perplexity-trap | canonical | 3 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| calibration | Ran | whydwelledonai/perplexity-trap/two_stage_reg.py pointer only (licence: NONE) · get_code("7ebebcb38608d145") |
| check_perplexity | Ran | whydwelledonai/perplexity-trap/calc_perplexity.py pointer only (licence: NONE) · get_code("8e2d5c790e62fb47") |
| concat_tokens | Ran | whydwelledonai/perplexity-trap/calc_perplexity.py pointer only (licence: NONE) · get_code("2e026803eaba99f9") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Previous studies have found that PLM-based retrieval models exhibit a preference for LLM-generated content, assigning higher relevance scores to these documents even when their semantic quality is comparable to human-written ones. This phenomenon, known as source bias, threatens the sustainable development of the information access ecosystem. However, the underlying causes of source bias remain unexplored. In this paper, we explain the process of information retrieval with a causal graph and discover that PLM-based retrievers learn perplexity features for relevance estimation, causing source bias by ranking the documents with low perplexity higher. Theoretical analysis further reveals that the phenomenon stems from the positive correlation between the gradients of the loss functions in language modeling task and retrieval task. Based on the analysis, a causal-inspired inferencetime debiasing method is proposed, called Causal Diagnosis and Correction (CDC). CDC first diagnoses the bias effect of the perplexity and then separates the bias effect from the overall estimated relevance score. Experimental results across three domains demonstrate the superior debiasing effectiveness of CDC, emphasizing the validity of our proposed explanatory framework 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2503.08684")
get_code_for_paper("2503.08684")
have("2503.08684")
Connect an agent — have() is free.