Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Govindarajan, Venkata S"'
The variations between in-group and out-group speech (intergroup bias) are subtle and could underlie many social phenomena like stereotype perpetuation and implicit bias. In this paper, we model the intergroup bias as a tagging task on English sports
Externí odkaz:
http://arxiv.org/abs/2406.17947
Techniques in causal analysis of language models illuminate how linguistic information is organized in LLMs. We use one such technique, AlterRep, a method of counterfactual probing, to explore the internal structure of multilingual models (mBERT and
Externí odkaz:
http://arxiv.org/abs/2310.18862
We present Lil-Bevo, our submission to the BabyLM Challenge. We pretrained our masked language models with three ingredients: an initial pretraining with music data, training on shorter sequences before training on longer ones, and masking specific t
Externí odkaz:
http://arxiv.org/abs/2310.17591
While existing work on studying bias in NLP focues on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social context, and its effects on language behavior. In this paper, we inves
Externí odkaz:
http://arxiv.org/abs/2305.16409
Autor:
Govindarajan, Venkata S, Atwell, Katherine, Sinno, Barea, Alikhani, Malihe, Beaver, David I., Li, Junyi Jessy
Current studies of bias in NLP rely mainly on identifying (unwanted or negative) bias towards a specific demographic group. While this has led to progress recognizing and mitigating negative bias, and having a clear notion of the targeted group is ne
Externí odkaz:
http://arxiv.org/abs/2209.06687
Autor:
Kovatchev, Venelin, Chatterjee, Trina, Govindarajan, Venkata S, Chen, Jifan, Choi, Eunsol, Chronis, Gabriella, Das, Anubrata, Erk, Katrin, Lease, Matthew, Li, Junyi Jessy, Wu, Yating, Mahowald, Kyle
Developing methods to adversarially challenge NLP systems is a promising avenue for improving both model performance and interpretability. Here, we describe the approach of the team "longhorns" on Task 1 of the The First Workshop on Dynamic Adversari
Externí odkaz:
http://arxiv.org/abs/2206.14729