Mark Whiting

M. Moran, Mark Whiting

Confidence-weighted routing, selective abstention, and ensemble weighting all assume that a model's stated confidence is informative about its capability on the question being asked. They presume functional metacognition, the capacity to assess one's own capabilities, without exercising them. Aggregate calibration is well studied, with mixed results, but the underlying structure of elicited confidence is less well understood. We decompose binary confidence judgements from 20 frontier Large Language Models (LLMs) across six benchmarks using tetrachoric factor analysis paired with pairwise calibration, asking whether two models that differ in confidence also differ in performance. On factual recall and information retrieval benchmarks the cross-model confidence matrix is approximately rank-one and a single dominant factor captures most of the latent variance. Models retrieving facts share an item-level difficulty axis and differ mainly in their decision thresholds along it. Across all benchmarks the relationship between confidence and performance collapses once items that all models agree on are removed. Inter-model pairwise calibration is small even where statistically significant, and what remains shrinks to nothing once base-rate differences along the shared factor are controlled for. Mathematical reasoning is the apparent exception, but this turns out to be a confound where reasoning models answer questions about their confidence by trying to solve them in their chain of thought, bypassing the sub-symbolic self-knowledge we seek to measure. We find no evidence for significant verbalised individuated metacognition in any tested domain.

Vinay K Chaudhri, Chaitan Baru, Brandon Bennett et al.

The long-standing goal of creating a comprehensive, multi-purpose knowledge resource, reminiscent of the 1984 Cyc project, still persists in AI. Despite the success of knowledge resources like WordNet, ConceptNet, Wolfram|Alpha and other commercial knowledge graphs, verifiable, general-purpose widely available sources of knowledge remain a critical deficiency in AI infrastructure. Large language models struggle due to knowledge gaps; robotic planning lacks necessary world knowledge; and the detection of factually false information relies heavily on human expertise. What kind of knowledge resource is most needed in AI today? How can modern technology shape its development and evaluation? A recent AAAI workshop gathered over 50 researchers to explore these questions. This paper synthesizes our findings and outlines a community-driven vision for a new knowledge infrastructure. In addition to leveraging contemporary advances in knowledge representation and reasoning, one promising idea is to build an open engineering framework to exploit knowledge modules effectively within the context of practical applications. Such a framework should include sets of conventions and social structures that are adopted by contributors.

Snehalkumar, S. Gaikwad, Durim Morina et al.

Paid crowdsourcing platforms suffer from low-quality work and unfair rejections, but paradoxically, most workers and requesters have high reputation scores. These inflated scores, which make high-quality work and workers difficult to find, stem from social pressure to avoid giving negative feedback. We introduce Boomerang, a reputation system for crowdsourcing that elicits more accurate feedback by rebounding the consequences of feedback directly back onto the person who gave it. With Boomerang, requesters find that their highly-rated workers gain earliest access to their future tasks, and workers find tasks from their highly-rated requesters at the top of their task feed. Field experiments verify that Boomerang causes both workers and requesters to provide feedback that is more closely aligned with their private opinions. Inspired by a game-theoretic notion of incentive-compatibility, Boomerang opens opportunities for interaction design to incentivize honest reporting over strategic dishonesty.

Snehalkumar "Neil" S. Gaikwad, Nalin Chhibber, Vibhor Sehgal et al.

Low-quality results have been a long-standing problem on microtask crowdsourcing platforms, driving away requesters and justifying low wages for workers. To date, workers have been blamed for low-quality results: they are said to make as little effort as possible, do not pay attention to detail, and lack expertise. In this paper, we hypothesize that requesters may also be responsible for low-quality work: they launch unclear task designs that confuse even earnest workers, under-specify edge cases, and neglect to include examples. We introduce prototype tasks, a crowdsourcing strategy requiring all new task designs to launch a small number of sample tasks. Workers attempt these tasks and leave feedback, enabling the re- quester to iterate on the design before publishing it. We report a field experiment in which tasks that underwent prototype task iteration produced higher-quality work results than the original task designs. With this research, we suggest that a simple and rapid iteration cycle can improve crowd work, and we provide empirical evidence that requester "quality" directly impacts result quality.

Dilrukshi Gamage, Mark Whiting, Thejan Rajapakshe et al.

Massive Open Online Courses (MOOCs) use peer assessment to grade open ended questions at scale, allowing students to provide feedback. Relative to teacher based grading, peer assessment on MOOCs traditionally delivers lower quality feedback and fewer learner interactions. We present the identified peer review (IPR) framework, which provides non-blind peer assessment and incentives driving high quality feedback. We show that, compared to traditional peer assessment methods, IPR leads to significantly longer and more useful feedback as well as more discussion between peers.