paper-with-me

홈 › Papers

$\texttt{ACCORD}$: Closing the Commonsense Measurability Gap

2024-06-04 · François Roewer-Després, Jinyue Feng, Zining Zhu, Frank Rudzicz

We present $\texttt{ACCORD}$, a framework and benchmark suite for disentangling the commonsense grounding and reasoning abilities of large language models (LLMs) through controlled, multi-hop counterfactuals. $\texttt{ACCORD}$ introduces formal elements to commonsense reasoning to explicitly control and quantify reasoning complexity beyond the typical 1 or 2 hops. Uniquely, $\texttt{ACCORD}$ can automatically generate benchmarks of arbitrary reasoning complexity, and so it scales with future LLM improvements. Benchmarking state-of-the-art LLMs -- including GPT-4o (2024-05-13), Llama-3-70B-Instruct, and Mixtral-8x22B-Instruct-v0.1 -- shows performance degrading to random chance with only moderate scaling, leaving substantial headroom for improvement. We release a leaderboard of the benchmark suite tested in this work, as well as code for automatically generating more complex benchmarks.

📄 PDF Abstract BibTeX arXiv:2406.02804

Code (1)

francois-rd/accord 공식 구현

Tasks

BenchmarkingCommon Sense ReasoningCounterfactual ReasoningLarge Language ModelQuestion Answering

Similar Papers 제목 키워드 기반

Null Measurability at the Symmetrization Interface in VC Learning

2026-04-27 · Dhruv Gupta arxiv

Recent work revisiting measurability in the fundamental theorem of statistical learning imposes Borel measurability of ghost-gap suprema. We show that, at the one-sided ghost-gap interface actually used by the standard s…

Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning

2026-02-22 · Jiahao Zhang, Lujing Zhang, Keltin Grimes, Zhuohao Yu 외 arxiv

A recurring challenge in preference fine-tuning (PFT) is handling $\textit{intransitive}$ (i.e., cyclic) preferences. Intransitive preferences often stem from either $\textit{(i)}$ inconsistent rankings along a single ob…

Instruction Following

Measurability in the Fundamental Theorem of Statistical Learning

2024-10-14 · Lothar Sebastian Krapp, Laura Wirth

The Fundamental Theorem of Statistical Learning states that a hypothesis space is PAC learnable if and only if its VC dimension is finite. For the agnostic model of PAC learning, the literature so far presents proofs of …

Binary ClassificationPAC learning

qPOTS: Efficient batch multiobjective Bayesian optimization via Pareto optimal Thompson sampling

2023-10-24 · Ashwin Renganathan, Kade E. Carlson

Classical evolutionary approaches for multiobjective optimization are quite accurate but incur a lot of queries to the objectives; this can be prohibitive when objectives are expensive oracles. A sample-efficient approac…

Bayesian OptimizationComputational EfficiencyMultiobjective OptimizationThompson Sampling

Model selection in hybrid quantum neural networks with applications to quantum transformer architectures

2026-03-23 · Harsh Wadhwa, Rahul Bhowmick, Naipunnya Raj, Rajiv Sangle 외 arxiv

Quantum machine learning models generally lack principled design guidelines, often requiring full resource-intensive training across numerous choices of encodings, quantum circuit designs and initialization strategies to…

Quantum Machine Learning