Large language models (LLMs) have an impressive ability to draw on novel information supplied in their context. Yet the mechanisms underlying this contextual grounding remain unknown, especially in situations where contextual information contradicts factual knowledge stored in the parameters, which LLMs also excel at recalling. Favoring the contextual information is critical for retrieval-augmented generation methods, which enrich the context with up-to-date information, hoping that grounding can rectify outdated or noisy stored knowledge. We present a novel method to study grounding abilities using Fakepedia, a novel dataset of counterfactual texts constructed to clash with a model’s internal parametric knowledge. In this study, we introduce Fakepedia, a counterfactual dataset designed to evaluate grounding abilities when the internal parametric knowledge clashes with the contextual information. We benchmark various LLMs with Fakepedia and conduct a causal mediation analysis of LLM components when answering Fakepedia queries, based on our Masked Grouped Causal Tracing (MGCT) method. Through this analysis, we identify distinct computational patterns between grounded and ungrounded responses. We finally demonstrate that distinguishing grounded from ungrounded responses is achievable through computational analysis alone. Our results, together with existing findings about factual recall mechanisms, provide a coherent narrative of how grounding and factual recall mechanisms interact within LLMs.

We ask whether multilingual language models trained on unbalanced, English-dominated corpora use English as an internal pivot language—-a question of key importance for understanding how language models function and the origins of linguistic bias. Focusing on the Llama-2 family of transformer models, our study is based on carefully constructed non-English prompts with a unique correct single-token continuation. From layer to layer, transformers gradually map an input embedding of the final prompt token to an output embedding from which next-token probabilities are computed. Tracking intermediate embeddings through their high-dimensional space reveals three distinct phases, whereby intermediate embeddings (1) start far away from output token embeddings; (2) already in middle layers allow for decoding a semantically correct next token, but giving higher probability to its version in English than in the input language; (3) move into an input-language-specific region of the embedding space. We cast these results into a conceptual model where the three phases operate in ”input space”, ”concept space”, and ”output space”, respectively. Crucially, our evidence suggests that the abstract ”concept space” lies closer to English than to other input languages, which may have important consequences regarding the biases embodied by multilingual language models.