arXiv AI
Count Evidence, Not Sentences: Tempered Evidence Fusion of LLM Judgments for Long-Text Value Measurement
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 2
Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach
arXiv:2605.28313v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in tasks related to reasoning and judgment. However, assessing the quality o...
arXiv AI
Sep 7
MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate
MABPD (Multi‑Agent Bias Probing & Detection) is a training‑free pipeline that uses three specialized large language model agents to analyze news articles from complementary perspectives and resolve disagreements via a Structured Argument Debate (SAD) protocol. SAD imposes an asymmetric burden of proof—biased claims lacking grounded textual evidence receive zero weight—along with role‑weighted voting and post‑consensus verification, replacing task‑specific supervised decision boundaries. Ablation studies show that the debate module alone accounts for up to a 10.6‑point F1 gain, and on the BABE benchmark MABPD attains 83.4% macro F1, within 0.7 percentage points of the supervised state‑of‑the‑art, while achieving 75.0% zero‑shot accuracy on the SemEval 2019 HyperPartisan corpus.
arXiv AI
Jun 12
More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts
arXiv:2605. 22641v3 Announce Type: replace-cross Abstract: Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions between neighboring values.
arXiv AI
Jun 12
Multiagent Protocols with Aggregated Confidence Signals
arXiv:2606. 13591v1 Announce Type: new Abstract: Confidence is used for reliability, oversight, and a range of downstream decision tasks in Natural Language Processing (NLP), yet no existing method produces or evaluates a confidence for the output of a multiagent system.
arXiv Computation and Language
Sep 2
PromptNCE: Conditional Probabilities and PMI Using Only LLMs and Contrastive Estimation Prompts
The paper introduces PromptNCE, a zero‑shot method that uses large language models to estimate pointwise mutual information (PMI) by framing conditional probability estimation as a contrastive task with an explicit OTHER category. The authors benchmark PromptNCE against four other prompting‑based estimators on three human‑annotated datasets, finding that PromptNCE achieves the best conditional probability estimates and Spearman correlations up to 0.78 for full PMI. A case study demonstrates the method’s utility for scoring student knowledge summaries in low‑data settings, and the authors release code and prompts for reproducibility.
arXiv AI
Sep 10
Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation
The paper introduces Fact-Ablated Evaluation (FAE), a framework that iteratively removes cited evidence to test whether large language models (LLMs) adjust their fact‑checking predictions accordingly. Experiments reveal that many off‑the‑shelf LLMs rely more on internal knowledge than on the provided evidence. To address this, the authors propose REAL, a training method that uses counterfactual evidence supervision to encourage LLMs to base veracity judgments on evidence, achieving better evidence‑dependent performance across four datasets.