Tag
This paper proposes DysLexLens, a low-resource LLM framework for analyzing dyslexic learners' experiences with AI tools using online forum data, featuring dictionary-driven filtering, knowledge-graph reasoning, and evaluation metrics.
This paper analyzes 1,500 open-ended responses from 75 countries to reveal that people have diverse and often conflicting preferences for AI, with truthfulness being the only widely demanded value (49%), yet defined in incompatible ways. It argues that current RLHF methods flatten these pluralistic preferences into universal reward models, perpetuating epistemic violence.
This paper proposes a multi-pass prompt verification method to improve the performance of quantized LLMs (LLaMA-3.1 8B) in qualitative analysis, reducing hallucinations and increasing stability across different quantization levels (8-bit, 4-bit, 3-bit, 2-bit).
Columbia and Northwestern researchers propose a pipeline to surface race and gender bias in LLM abstractive summaries of life-story interviews, showing representational harm risks.