arXiv AI
Jul 14
Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction
arXiv:2607. 11696v1 Announce Type: new Abstract: Self-refinement often fails to strengthen few-shot inductive reasoning in large language models.
Can LLMs in Draft-Verify-Revise Pipelines Resolve Deictic Ambiguity?
The study investigates how deictic ambiguity—specifically the shifting reference of expressions like "previous"—affects Draft‑Verify‑Revise pipelines that use multiple large language models (LLMs). Using a synthetic dataset of 10 base examples and 21 reasoning‑effort configurations, six LLMs were evaluated for their ability to correctly resolve the ambiguous expression across the draft, verify, and revise stages. Results show wide variance in balanced accuracy, with GPT‑5.2 improving from 0.156 to 0.942 with increased reasoning effort, while Gemini 3 Pro consistently achieved high accuracy above 0.94 even at low reasoning effort, and meta‑evaluators often relied on surface cues when making errors.
Related stories
arXiv AI
Aug 11
Reproducing and Stress-Testing Two Approaches to LLM Reasoning Reliability: Test-Time Probability Aggregation and Logic-Representation Editing
arXiv:2608. 08514v1 Announce Type: new Abstract: We independently reproduce two recent methods for making large language model (LLM) reasoning more reliable, and stress-test them across domains and models (RPC across four new task domains with Qwen3-8B, LCF across four 7-8B models).
arXiv AI
Sep 10
CausalVerify: An Execution-Grounded Benchmark for LLM Causal Inference Workflows
arXiv:2609.07944v1 Announce Type: new Abstract: Existing causal-inference benchmarks for LLMs mostly score method descriptions or whether generated code runs, not whether the executed workflow recove...
arXiv AI
Jul 22
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
arXiv:2607. 19257v1 Announce Type: cross Abstract: Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade.
Hugging Face Trending Papers
Jul 21
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade. We report two controlled experiments crossing all three factors on one held, contamination-free synthetic corpus (the "Book of Veyra," 8,780 uniquely-named entities, deterministically regenerable from a fixed seed), evaluated across five models.
arXiv Computation and Language
3d ago
Draft-OPD: On-Policy Distillation for Speculative Draft Models
Draft-OPD introduces an on‑policy distillation method for speculative draft models, addressing the mismatch between supervised fine‑tuning and inference by letting the target model supervise the drafter on draft‑induced states. The approach uses target‑assisted rollouts for stable continuations and replays drafting from error positions exposed during verification, enabling the drafter to learn from both accepted and rejected proposals. Experiments demonstrate that Draft‑OPD achieves more than five‑fold lossless acceleration across diverse tasks, outperforming prior draft models such as EAGLE‑3 and DFlash by 23 % and 13 % respectively.
arXiv AI
Aug 5
The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics
arXiv:2608. 03291v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process.
arXiv AI
Jul 15
Rethinking Reward Models for Multi-Domain Test-Time Scaling
arXiv:2510. 00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic.
arXiv Machine Learning
22h ago
ChipMEM: Verification-Grounded Memory for EDA Agents
ChipMEM introduces a verification‑grounded memory layer for electronic design automation agents that combines cross‑task procedural memory with within‑trajectory statistical guidance. The procedural component stores a skill only after it passes synthesis, simulation, or formal checks, while a Bayesian component ranks recovery strategies based on tool‑call outcomes. Experiments on RTLRewriter‑Bench and CVDP tasks show that ChipMEM improves equivalence‑passing outputs and area metrics compared to agents without memory.
arXiv AI
Jul 21
Constrained Path Reasoning: Measuring When Committed Stages Earn Their Cost
arXiv:2607. 17240v1 Announce Type: new Abstract: When does a committed intermediate stage in an LLM reasoning pipeline earn its cost?
arXiv Computation and Language
Aug 21
Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning
arXiv:2608. 19009v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that claim to detect the model's errors.
arXiv AI
Aug 18
Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion
arXiv:2608. 14617v1 Announce Type: cross Abstract: A recurring proposal in legal AI is to improve case-outcome prediction by fusing uncertainty tools (evidence graphs with belief propagation, sequential Bayesian odds updating, Dempster-Shafer combination, and conformal prediction) into one pipeline.