Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.29637 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910269285859328 |
|---|---|
| author | Mazumder, Debajyoti Pathak, Divyansh Kodali, Prashant Joshi, Aditya Agarwal, Akshay Patro, Jasabanta |
| author_facet | Mazumder, Debajyoti Pathak, Divyansh Kodali, Prashant Joshi, Aditya Agarwal, Akshay Patro, Jasabanta |
| contents | Large language models recall knowledge reliably in English but often fail on the same query posed in a lower-resourced language -- a crosslingual consistency gap that remains underexplored for Indian languages and their code-mixed counterparts. To study this gap, we introduce IndiKLAR, an Indic extension of the KLAR-CLC benchmark covering 18 of the 22 scheduled Indian languages and pairing them with code-mixed variants for 11 widely used language pairs, with native-speaker verification of both monolingual and code-mixed variants for these 11 settings. This three-way alignment offers a unique opportunity to examine how knowledge recall consistency varies across the spectrum of English, code-mixed, and native Indian language inputs. Evaluating across nine open-weight models, we find that the native-language accuracy gap to English can reach $\sim$0.50, while code-mixed inputs close most of it -- bringing performance within $\sim$0.05 of English without any model-level intervention. Motivated by this, we evaluate several prompting strategies that vary in how language conversion is exposed, including a two-stage translate-then-answer setup, a one-stage joint translation-and-answer prompt, and Translate-in-Thought (TinT) -- a single-step strategy in which the model converts the input internally and emits only the final answer. Across the performance trajectory native $\rightarrow$ code-mixed $\rightarrow$ English, we identify a consistent flip point -- the boundary between incorrect and correct prediction -- that lies between the native and code-mixed settings. Interestingly, this holds whether the trajectory is induced by the input surface form or by the model's internal conversion process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29637 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evaluating Cross-lingual Knowledge Consistency in Code-Mixed vis-a-vis Indian Languages using IndicKLAR Mazumder, Debajyoti Pathak, Divyansh Kodali, Prashant Joshi, Aditya Agarwal, Akshay Patro, Jasabanta Computation and Language Large language models recall knowledge reliably in English but often fail on the same query posed in a lower-resourced language -- a crosslingual consistency gap that remains underexplored for Indian languages and their code-mixed counterparts. To study this gap, we introduce IndiKLAR, an Indic extension of the KLAR-CLC benchmark covering 18 of the 22 scheduled Indian languages and pairing them with code-mixed variants for 11 widely used language pairs, with native-speaker verification of both monolingual and code-mixed variants for these 11 settings. This three-way alignment offers a unique opportunity to examine how knowledge recall consistency varies across the spectrum of English, code-mixed, and native Indian language inputs. Evaluating across nine open-weight models, we find that the native-language accuracy gap to English can reach $\sim$0.50, while code-mixed inputs close most of it -- bringing performance within $\sim$0.05 of English without any model-level intervention. Motivated by this, we evaluate several prompting strategies that vary in how language conversion is exposed, including a two-stage translate-then-answer setup, a one-stage joint translation-and-answer prompt, and Translate-in-Thought (TinT) -- a single-step strategy in which the model converts the input internally and emits only the final answer. Across the performance trajectory native $\rightarrow$ code-mixed $\rightarrow$ English, we identify a consistent flip point -- the boundary between incorrect and correct prediction -- that lies between the native and code-mixed settings. Interestingly, this holds whether the trajectory is induced by the input surface form or by the model's internal conversion process. |
| title | Evaluating Cross-lingual Knowledge Consistency in Code-Mixed vis-a-vis Indian Languages using IndicKLAR |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.29637 |