Papers › How Language Models Prioritize Contextual Grammatical Cues?

How Language Models Prioritize Contextual Grammatical Cues?

4 Oct 2024arXiv:2410.03447archive 2025-07-28

Hamidreza Amirzadeh, Afra Alishahi, Hosein Mohebbi

Transformer-based language models have shown an excellent ability to effectively capture and utilize contextual information. Although various analysis techniques have been used to quantify and trace the contribution of single contextual cues to a target task such as subject-verb agreement or coreference resolution, scenarios in which multiple relevant cues are available in the context remain underexplored. In this paper, we investigate how language models handle gender agreement when multiple gender cue words are present, each capable of independently disambiguating a target gender pronoun. We analyze two widely used Transformer-based models: BERT, an encoder-based, and GPT-2, a decoder-based model. Our analysis employs two complementary approaches: context mixing analysis, which tracks information flow within the model, and a variant of activation patching, which measures the impact of cues on the model's prediction. We find that BERT tends to prioritize the first cue in the context to form both the target word representations and the model's prediction, while GPT-2 relies more on the final cue. Our findings reveal striking differences in how encoder-based and decoder-based models prioritize and use contextual information for their predictions.

Paper PDF Code

Code

hamid-amir/CueWords officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Coreference Resolution Decoder coreference-resolution

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam Attention Attention Dropout BERT BPE Cosine Annealing Dense Connections Discriminative Fine-Tuning Dropout GPT-2 Layer Normalization Linear Layer Linear Warmup With Cosine Annealing Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections