REVIEW 21 cited by
MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
read the original abstract
While large language models (LLMs) equipped with techniques like chain-of-thought prompting have demonstrated impressive capabilities, they still fall short in their ability to reason robustly in complex settings. However, evaluating LLM reasoning is challenging because system capabilities continue to grow while benchmark datasets for tasks like logical deduction have remained static. We introduce MuSR, a dataset for evaluating language models on multistep soft reasoning tasks specified in a natural language narrative. This dataset has two crucial features. First, it is created through a novel neurosymbolic synthetic-to-natural generation algorithm, enabling the construction of complex reasoning instances that challenge GPT-4 (e.g., murder mysteries roughly 1000 words in length) and which can be scaled further as more capable LLMs are released. Second, our dataset instances are free text narratives corresponding to real-world domains of reasoning; this makes it simultaneously much more challenging than other synthetically-crafted benchmarks while remaining realistic and tractable for human annotators to solve with high accuracy. We evaluate a range of LLMs and prompting techniques on this dataset and characterize the gaps that remain for techniques like chain-of-thought to perform robust reasoning.
Forward citations
Cited by 21 Pith papers
-
Will Scaling Improve Social Simulation with LLMs?
Scaling improves LLM social simulation fidelity in most opinion and behavior tasks but not for human cognitive bias calibration or low-resource domains.
-
Forecasting Future Behavior as a Learning Task
Behavior Forecasters trained on LRM trajectories outperform larger models in predicting repeatability and input sensitivity at low cost.
-
Not only where, But when: Temporal Scheduling for RLVR
Temporal scheduling of credit allocation criteria over RLVR training, using trajectory percentiles to target heterogeneous behaviors, yields more stable policy entropy and better reasoning benchmark results than stati...
-
Large Language Model Selection with Limited Annotations
SELECT-LLM is the first active model selection framework for LLMs that uses expected information gain from pairwise output similarities to minimize required annotations, reporting up to 84.78% cost reduction across 23...
-
LitVISTA: A Benchmark for Narrative Orchestration in Literary Text
LitVISTA benchmark shows frontier LLMs fail to jointly capture narrative function and structure in literary texts, with errors dominated by anchor identification.
-
PRIMETIME : Limits of LLMs in Temporal Primitives
PRIMETIME generator reveals that LLM datetime parsing and arithmetic primitives are individually unreliable but fully learnable via fine-tuning, enabling frontier-level accuracy on event planning with small LoRA models.
-
Will Scaling Improve Social Simulation with LLMs?
Using 85 controlled and 35 public LLMs, the authors show social-simulation accuracy generally improves with compute, but some behavioral and low-resource tasks do not scale.
-
Quantifying Faithful Confidence Expression in Large Reasoning Models
A new framework quantifies faithful confidence expression in large reasoning models by comparing linguistic decisiveness to token probabilities, hidden states, and response consistency, revealing it as a persistent challenge.
-
SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
A 24-dataset benchmark for inducing schema graphs from raw text, plus an auditable LLM-based pipeline that reports the highest scores on the benchmark's four schema-similarity metrics.
-
Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning
BET reduces reasoning tokens by about 55% on average while improving performance across benchmarks by learning to short-solve easy queries, fold early on unsolvable ones, and preserve budget for hard solvable queries.
-
An Interpretable and Scalable Framework for Evaluating Large Language Models
A majorization-minimization framework turns IRT into scalable matrix factorization subproblems for LLM evaluation, delivering orders-of-magnitude speedups with identifiability guarantees.
-
TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models
TDA-RC embeds topological patterns from multi-round reasoning into CoT via persistent homology and a repair agent, yielding better accuracy-efficiency trade-offs than ToT or GoT on tested datasets.
-
When LLMs get significantly worse: A statistical approach to detect model degradations
A McNemar-based statistical test detects real degradations in optimized LLMs with controlled false positives, even for accuracy changes as small as 0.3%.
-
f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
f-GRPO and f-HAL estimate f-divergences between reward-aligned and reward-unaligned response distributions and prove expected reward improvement for general LLM alignment.
-
LLaDA2.0: Scaling Up Diffusion Language Models to 100B
LLaDA2.0 scales discrete diffusion language models to 100B parameters via systematic conversion from autoregressive models using a 3-phase WSD training scheme and releases open-source 16B and 100B MoE variants.
-
Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource
MoE models with activation rates in an optimal region outperform dense LLMs of identical total parameter count, training compute, and data budget, with the optimal region consistent across scales.
-
UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types
UNA unifies binary, pairwise, and score-based feedback for LLM alignment via a generalized implicit reward function shown optimal by the log sum inequality.
-
Decision Protocols in Multi-Agent Large Language Model Conversations
Consensus decision protocols beat voting/judge on knowledge QA for Llama-3 multi-agent chats, while voting and judge win on logic tasks; independent initial drafts raise accuracy and extra voting-time info barely helps.
-
Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
Mid-training LLMs on self-generated diverse reasoning paths improves subsequent RL performance on mathematical benchmarks and OOD tasks.
-
Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
Attention sinks forge native MoE mechanisms in attention layers that cause head collapse, addressed by sink-aware training with auxiliary load balancing.
-
Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
Attention-sink weight is recast as an implicit MoE router per head, motivating a sink-aware head-balancing loss that yields small, consistent benchmark gains across three attention variants but rests on a definitional...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.