5 papers
Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation
Amruta Parulekar, Jinu Lee, Dilek Hakkani-Tür +1
Large Language Models (LLMs) explore problems through chain-of-thought, but this exploration is buried in unstructured prose. On high-stakes tasks, users cannot tell which steps ar…
Toxic HallucinAItions: Perturbing Prompts and Tracing LLM Circuits
Soorya Ram Shimgekar, Agam Goyal, Amruta Parulekar +6
Large language models (LLMs) are increasingly deployed in conversational settings where user tone ranges from polite to adversarial or toxic, yet less is known about whether toxic…
Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG
Agam Goyal, Koyel Mukherjee, Apoorv Saxena +3
Dense retrievers in retrieval-augmented generation (RAG) systems exhibit systematic biases -- including brevity, position, literal matching, and repetition biases -- that can compr…
CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
Yian Wang, Yuen Chen, Agam Goyal +1
Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrade generation quality or requ…
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
Weixiang Yan, Haitian Liu, Yunkun Wang +8
Large Language Models (LLMs) have demonstrated remarkable performance on assisting humans in programming and facilitating programming automation. However, existing benchmarks for e…