Vidhisha Balachandran, Yulia Tsvetkov, Shangbin Feng, Weijia Shi, Sunayana Sitaram, Yike Wang, Wenxuan Ding, Orevaoghene Ahia, S. Li
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Multilingual large language models (LLMs) often have knowledge disparities across languages, with larger gaps in under-resourced languages. Teaching LLMs to abstain in the face of knowledge gaps is thus a promising strategy to mitigate hallucinations in multilingual settings. However, previous studies on LLM abstention primarily focus on English; we find that directly applying these solutions beyond English results in up to 20.5% performance gaps between high and low-resource languages, potentially due to LLMs' drop in calibration and reasoning beyond a few resource-rich languages. To this end, we propose strategies to enhance LLM abstention by learning from multilingual feedback, where LLMs self-reflect on proposed answers in one language by generating multiple feedback items in related languages: we show that this helps identify the knowledge gaps across diverse languages, cultures, and communities. Extensive experiments demonstrate that our multilingual feedback approach outperforms various strong baselines, achieving up to 9.2% improvement for lowresource languages across three black-box and open models on three datasets, featuring openbook, closed-book, and commonsense QA. Further analysis reveals that multilingual feedback is both an effective and a more equitable abstain strategy to serve diverse language speakers, and cultural factors have great impact on language selection and LLM abstention behavior, highlighting future directions for multilingual and multi-cultural reliable language modeling. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.15948")
get_code_for_paper("2406.15948")
have("2406.15948")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.15948.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.15948)
Connect an agent — have() is free.