Papers with TRACE

11 papers
TRACE: Training and Inference-Time Interpretability Analysis for Language Models (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing tools for interpretability analysis of transformer models are post hoc, rely on scalar metrics or require nontrivial integration effort.
Approach: They propose a modular toolkit for training and inference-time interpretability analysis of transformer models.
Outcome: Experiments with autoregressive transformers show that TRACE reveals developmental phenomena overlooked by traditional scalar metrics such as loss or accuracy.
TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for multihop Knowledge Graph Question Answering (KGQA) treat each reasoning step independently and fail to leverage experience from prior explorations, leading to fragmented reasoning and redundant exploration.
Approach: They propose a framework that unifies LLM-driven contextual reasoning with exploration prior integration to enhance coherence and robustness of multihop KGQA.
Outcome: Extensive experiments on multiple KGQA benchmarks show that TRACE outperforms state-of-the-art methods.
Hearing Between the Lines: Unlocking the Reasoning Power of LLMs for Speech Evaluation (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Model (LLM) judges are limited to textual content, resulting in expensive and opaque evaluation methods.
Approach: They propose a framework that enables large language model judges to reason over audio cues . they introduce a human chain-of-thought annotation protocol to improve judge diagnostic capability .
Outcome: The proposed framework achieves higher agreement with human raters than ALMs and transcript-only LLM judges while being significantly more cost-effective.
TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Evaluating large vision-language models has focused on final-answer correctness, but this metric is often insufficient and misleading.
Approach: They propose a framework that decomposes complex multimodal tasks into Auxiliary Reasoning Sets (ARS) ARS decomposition reveals how consistently a model reasons across sub-questions with structured dependencies.
Outcome: a new framework improves diagnostic evaluation of large vision-language models . it decomposes complex multimodal tasks into auxiliary reasoning sets with structured dependencies . the framework pinpoints reasoning failures and exposes errors overlooked by standard evaluation .
TRACE: Traversal Retrieval-Augmented Chain of Evidence for Document Understanding (2026.acl-long)

Copied to clipboard

Challenge: Long-context Document Visual Question Answering (DocVQA) methods struggle with visual semantics or handling finite context windows.
Approach: They propose a new approach to longcontext document visual question answering that transforms retrieval into adaptive evidence chain construction using a Bi-Layered Graph.
Outcome: The proposed approach achieves an average accuracy improvement of 14.07% on M5BookVQA and exhibits robust generalization with a 13.38% gain across four established benchmarks.
Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation (2022.findings-emnlp)

Copied to clipboard

Challenge: Variational Auto-Encoder (VAE) has been widely adopted in text generation due to its ability to learn flexible representations.
Approach: They propose a Transformer-based recurrent VAE structure that imposes recurrence on segment-wise latent variables with arbitrarily separated text segments and constructs the posterior distribution with residual parameterization.
Outcome: The proposed structure can deduce a non-zero lower bound of the KL term and enhance the entanglement of each segment and preceding latent variables, providing a theoretical guarantee of generation diversity.
TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing retrievers are not perfect and often include irrelevant documents in the retrieved set.
Approach: They propose to construct knowledge-grounded reasoning chains from retrieved documents to integrate supporting evidence into RAG models.
Outcome: The proposed model achieves an average performance improvement of 14.03% on three multi-hop QA datasets.
Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing Multimodal Large Language Models struggle with 3D spatial reasoning as they fail to construct structured abstractions of the 3D environment depicted in video inputs.
Approach: They propose a prompting method that induces MLLMs to generate 3D representations as reasoning traces for more accurate spatial question answering.
Outcome: Extensive experiments on VSI-Bench and OST-Bech show that TRACE improves over prior prompting strategies across a diverse range of MLLM backbones.
Efficient Test-Time Scaling via Temporal Reasoning Aggregation (2026.findings-acl)

Copied to clipboard

Challenge: Existing dynamic early-exit methods rely on single-step confidence signals . existing approaches are unreliable for detecting reasoning convergence in multi-step settings .
Approach: They propose a training-free framework for efficient test-time scaling that determines when to terminate reasoning based on temporal aggregation of multi-step evidence rather than instantaneous signals.
Outcome: Experiments show that TRACE reduces reasoning token usage by 25% on average while maintaining accuracy within 1–2% of full-length reasoning.
Do LLMs Really Need 10+ Thoughts for “Find the Time 1000 Days Later”? Towards Structural Understanding of LLM Overthinking (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on LLMs' thought processes are limited to superficial, profiling-based observations, failing to delve into their inner workings.
Approach: They propose a utility-based definition of overthinking that moves beyond length-based metrics and provides a more insightful understanding of LLMs' thought progression.
Outcome: The proposed model decomposes the LLM thought process into minimally complete sub-thoughts and identifies common thinking patterns for topically similar queries.
TRACE: Two-Phase RL for Causal Graph Exploration and Deeper Psychological Intervention in Dynamic Counseling Scenarios (2026.findings-acl)

Copied to clipboard

Challenge: Existing models lack the ability to actively explore the underlying causes of psychological distress.
Approach: They propose a two-phase reinforcement learning framework that implements a causal-graph-driven reward scheme across two phases: an exploration phase that rewards the causal graph reconstruction following a surface-to-deep path, and an intervention phase that supports targeted restructuring of irrational beliefs.
Outcome: Extensive experiments show that TRACE outperforms existing models, enabling causal-chain-aware psychological intervention beyond surface-level empathy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations